A survey on deep learning techniques for image and video semantic segmentation
•An in-depth review of deep learning methods for semantic segmentation applied to various areas.•An overview of background concepts and formulation for newcomers.•A structured and logical review of datasets and methods, highlighting their contributions and significance.•Quantitative comparison of pe...
Saved in:
| Published in | Applied soft computing Vol. 70; pp. 41 - 65 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.09.2018
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •An in-depth review of deep learning methods for semantic segmentation applied to various areas.•An overview of background concepts and formulation for newcomers.•A structured and logical review of datasets and methods, highlighting their contributions and significance.•Quantitative comparison of performance and accuracy on common datasets.•A discussion of future works and promising research lines and conclusions about the state of the art of the field.
Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation, and even virtual or augmented reality systems to name a few. This demand coincides with the rise of deep learning approaches in almost every field or application target related to computer vision, including semantic segmentation or scene understanding. This paper provides a review on deep learning methods for semantic segmentation applied to various application areas. Firstly, we formulate the semantic segmentation problem and define the terminology of this field as well as interesting background concepts. Next, the main datasets and challenges are exposed to help researchers decide which are the ones that best suit their needs and goals. Then, existing methods are reviewed, highlighting their contributions and their significance in the field. We also devote a part of the paper to review common loss functions and error metrics for this problem. Finally, quantitative results are given for the described methods and the datasets in which they were evaluated, following up with a discussion of the results. At last, we point out a set of promising future works and draw our own conclusions about the state of the art of semantic segmentation using deep learning techniques. |
|---|---|
| AbstractList | •An in-depth review of deep learning methods for semantic segmentation applied to various areas.•An overview of background concepts and formulation for newcomers.•A structured and logical review of datasets and methods, highlighting their contributions and significance.•Quantitative comparison of performance and accuracy on common datasets.•A discussion of future works and promising research lines and conclusions about the state of the art of the field.
Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation, and even virtual or augmented reality systems to name a few. This demand coincides with the rise of deep learning approaches in almost every field or application target related to computer vision, including semantic segmentation or scene understanding. This paper provides a review on deep learning methods for semantic segmentation applied to various application areas. Firstly, we formulate the semantic segmentation problem and define the terminology of this field as well as interesting background concepts. Next, the main datasets and challenges are exposed to help researchers decide which are the ones that best suit their needs and goals. Then, existing methods are reviewed, highlighting their contributions and their significance in the field. We also devote a part of the paper to review common loss functions and error metrics for this problem. Finally, quantitative results are given for the described methods and the datasets in which they were evaluated, following up with a discussion of the results. At last, we point out a set of promising future works and draw our own conclusions about the state of the art of semantic segmentation using deep learning techniques. |
| Author | Garcia-Garcia, Alberto Villena-Martinez, Victor Martinez-Gonzalez, Pablo Oprea, Sergiu Garcia-Rodriguez, Jose Orts-Escolano, Sergio |
| Author_xml | – sequence: 1 givenname: Alberto orcidid: 0000-0002-9575-6403 surname: Garcia-Garcia fullname: Garcia-Garcia, Alberto email: agarcia@dtic.ua.es – sequence: 2 givenname: Sergio orcidid: 0000-0001-6817-6326 surname: Orts-Escolano fullname: Orts-Escolano, Sergio email: sorts@ua.es – sequence: 3 givenname: Sergiu surname: Oprea fullname: Oprea, Sergiu email: soprea@dtic.ua.es – sequence: 4 givenname: Victor surname: Villena-Martinez fullname: Villena-Martinez, Victor email: vvillena@dtic.ua.es – sequence: 5 givenname: Pablo surname: Martinez-Gonzalez fullname: Martinez-Gonzalez, Pablo email: pmartinez@dtic.ua.es – sequence: 6 givenname: Jose surname: Garcia-Rodriguez fullname: Garcia-Rodriguez, Jose email: jgarcia@dtic.ua.es |
| BookMark | eNp9kM1uAiEUhUljk6rtC3TFC8wUmAGZpBtj-peYduOeIFwsRsHCaOLbFzNddeHqnM13c-43QaMQAyD0SElNCRVP21rnaGpGqKwJr0vcoDGVM1Z1QtJR6VzIqu1acYcmOW9JgTomx-hzjvMxneCMY8AW4IB3oFPwYYN7MN_B_xwhYxcT9nu9AayDxSdvIeIMex16b0rZ7CH0uvcx3KNbp3cZHv5yilavL6vFe7X8evtYzJeVaQjpK8dZ22nTOiGkY50B2hDXWbfm6zWHxmlnqCYW3EzMBOdWG0lkS5lxpIGONlPEhrMmxZwTOHVIZV86K0rURYjaqosQdRGiCFclCiT_QcYPq_uk_e46-jygUH46eUgqGw_BgPUJTK9s9NfwXz1MgAg |
| CitedBy_id | crossref_primary_10_1007_s11042_023_17292_8 crossref_primary_10_1016_j_ndteint_2020_102341 crossref_primary_10_1109_TIM_2024_3378205 crossref_primary_10_3390_rs12030423 crossref_primary_10_1175_JTECH_D_19_0146_1 crossref_primary_10_1016_j_eswa_2025_126726 crossref_primary_10_3390_electronics12244926 crossref_primary_10_3390_s19204599 crossref_primary_10_3390_s25010251 crossref_primary_10_1109_ACCESS_2021_3133276 crossref_primary_10_3390_agriculture12071033 crossref_primary_10_3390_app11020782 crossref_primary_10_3390_rs13183691 crossref_primary_10_3390_ijms21186737 crossref_primary_10_1016_j_aej_2022_06_045 crossref_primary_10_3390_rs14143415 crossref_primary_10_1109_ACCESS_2021_3077006 crossref_primary_10_3390_diagnostics9030072 crossref_primary_10_3390_rs15133268 crossref_primary_10_1007_s12559_024_10304_1 crossref_primary_10_1515_bmt_2023_0331 crossref_primary_10_3390_rs15194649 crossref_primary_10_1145_3329784 crossref_primary_10_3390_rs12213547 crossref_primary_10_3390_rs16234614 crossref_primary_10_1016_j_compag_2023_107805 crossref_primary_10_3390_agriengineering6040277 crossref_primary_10_1007_s10040_023_02672_z crossref_primary_10_1109_TNNLS_2021_3056384 crossref_primary_10_61186_jgit_10_4_87 crossref_primary_10_1007_s11042_019_08545_6 crossref_primary_10_1016_j_patcog_2022_108586 crossref_primary_10_1016_j_measurement_2022_110778 crossref_primary_10_1016_j_neucom_2021_04_061 crossref_primary_10_3390_technologies8010001 crossref_primary_10_1016_j_asoc_2024_111363 crossref_primary_10_1088_1748_3190_ababb0 crossref_primary_10_3390_rs12213537 crossref_primary_10_1016_j_compag_2024_109244 crossref_primary_10_1016_j_inffus_2021_09_018 crossref_primary_10_1016_j_jmapro_2022_11_018 crossref_primary_10_1109_TGRS_2023_3276591 crossref_primary_10_3390_app10144945 crossref_primary_10_1186_s12938_022_01058_8 crossref_primary_10_1007_s10489_021_02769_6 crossref_primary_10_1016_j_engfailanal_2024_108632 crossref_primary_10_1002_esp_70007 crossref_primary_10_1016_j_jfca_2023_105746 crossref_primary_10_1016_j_matchar_2022_112175 crossref_primary_10_1088_1361_6501_ad01ce crossref_primary_10_1049_ipr2_13045 crossref_primary_10_3390_mi14040879 crossref_primary_10_3390_s25061824 crossref_primary_10_1016_j_autcon_2020_103383 crossref_primary_10_1016_j_image_2021_116410 crossref_primary_10_3390_rs12142274 crossref_primary_10_1002_adem_201901197 crossref_primary_10_3390_s25010271 crossref_primary_10_1007_s00521_021_06397_6 crossref_primary_10_1016_j_compag_2024_109274 crossref_primary_10_1016_j_jbiomech_2024_112012 crossref_primary_10_1088_1742_6596_2718_1_012062 crossref_primary_10_1016_j_conbuildmat_2021_126265 crossref_primary_10_3390_s20185411 crossref_primary_10_1007_s11042_020_08862_1 crossref_primary_10_17694_bajece_1024073 crossref_primary_10_3390_cancers13112766 crossref_primary_10_3390_rs14225862 crossref_primary_10_1016_j_ecoinf_2022_101641 crossref_primary_10_1007_s11554_020_01021_7 crossref_primary_10_1109_TSE_2023_3285280 crossref_primary_10_1007_s00603_024_03824_7 crossref_primary_10_1016_j_dibe_2023_100283 crossref_primary_10_3390_rs12182932 crossref_primary_10_1016_j_asoc_2022_109500 crossref_primary_10_1016_j_neucom_2024_129264 crossref_primary_10_3390_rs13050905 crossref_primary_10_1007_s11042_021_11722_1 crossref_primary_10_1016_j_asr_2024_03_053 crossref_primary_10_3390_agriengineering7010011 crossref_primary_10_1016_j_neucom_2017_09_071 crossref_primary_10_3390_rs15020379 crossref_primary_10_1016_j_powtec_2022_117655 crossref_primary_10_3390_rs15030588 crossref_primary_10_1007_s10462_021_09967_1 crossref_primary_10_3390_ijgi12110454 crossref_primary_10_1016_j_engstruct_2022_115158 crossref_primary_10_1186_s13640_023_00613_0 crossref_primary_10_1016_j_scitotenv_2021_145191 crossref_primary_10_3390_agriculture14040637 crossref_primary_10_1016_j_ribaf_2024_102447 crossref_primary_10_1016_j_jvcir_2024_104167 crossref_primary_10_1007_s13632_020_00676_9 crossref_primary_10_1088_1361_6501_aca991 crossref_primary_10_1002_rob_21915 crossref_primary_10_1016_j_caeo_2024_100181 crossref_primary_10_1016_j_compag_2021_106191 crossref_primary_10_3390_electronics12051199 crossref_primary_10_3390_jmse11122268 crossref_primary_10_3390_a13090226 crossref_primary_10_1016_j_engappai_2023_106669 crossref_primary_10_1016_j_inpa_2021_01_004 crossref_primary_10_3390_f13071133 crossref_primary_10_1016_j_scitotenv_2023_168696 crossref_primary_10_1177_0278364920907688 crossref_primary_10_1080_22797254_2024_2343531 crossref_primary_10_1016_j_knosys_2021_107187 crossref_primary_10_1007_s00345_024_04775_y crossref_primary_10_1016_j_compag_2023_108065 crossref_primary_10_3390_s23094287 crossref_primary_10_1109_TITS_2022_3142393 crossref_primary_10_4018_JITR_299388 crossref_primary_10_1109_TGRS_2023_3245603 crossref_primary_10_3390_rs11222631 crossref_primary_10_3390_f14020244 crossref_primary_10_1109_COMST_2018_2869360 crossref_primary_10_1049_2024_9929900 crossref_primary_10_3390_s21010056 crossref_primary_10_1016_j_neuroimage_2021_117934 crossref_primary_10_1016_j_compag_2023_108073 crossref_primary_10_1038_s41598_023_28586_0 crossref_primary_10_3233_JIFS_233498 crossref_primary_10_4995_var_2021_15329 crossref_primary_10_1002_stc_2899 crossref_primary_10_1587_transinf_2023EDP7009 crossref_primary_10_3390_fi14100277 crossref_primary_10_3390_rs15051240 crossref_primary_10_3390_app122412606 crossref_primary_10_53508_ijiam_1406569 crossref_primary_10_1016_j_eswa_2022_116926 crossref_primary_10_3390_rs13214445 crossref_primary_10_1016_j_tust_2018_04_002 crossref_primary_10_1007_s11042_020_09185_x crossref_primary_10_3390_rs14112519 crossref_primary_10_1007_s11102_019_01026_x crossref_primary_10_1109_TNNLS_2022_3142181 crossref_primary_10_1364_PRJ_428425 crossref_primary_10_1016_j_neucom_2018_06_059 crossref_primary_10_3390_s19163576 crossref_primary_10_1016_j_buildenv_2024_112303 crossref_primary_10_35940_ijaent_A9759_12101223 crossref_primary_10_1145_3453651 crossref_primary_10_3390_s23031731 crossref_primary_10_1016_j_compag_2019_104874 crossref_primary_10_1016_j_jbi_2020_103526 crossref_primary_10_1007_s10462_022_10294_2 crossref_primary_10_1016_j_measurement_2023_113034 crossref_primary_10_3233_SJI_190555 crossref_primary_10_1002_qj_4153 crossref_primary_10_1109_ACCESS_2022_3202931 crossref_primary_10_3390_rs14051249 crossref_primary_10_11834_jig_230605 crossref_primary_10_3390_rs14020305 crossref_primary_10_3390_rs12020207 crossref_primary_10_3390_rs16111987 crossref_primary_10_1016_j_wasman_2022_02_009 crossref_primary_10_3390_s19040810 crossref_primary_10_34133_2020_4152816 crossref_primary_10_1109_JOE_2022_3219129 crossref_primary_10_3390_mi13020300 crossref_primary_10_1016_j_asoc_2020_106702 crossref_primary_10_12677_CSA_2022_122033 crossref_primary_10_3390_s24186016 crossref_primary_10_1016_j_jisa_2023_103434 crossref_primary_10_35414_akufemubid_1278080 crossref_primary_10_3390_rs14030582 crossref_primary_10_3390_cancers13184674 crossref_primary_10_3389_fpubh_2023_1025746 crossref_primary_10_1038_s41467_023_41260_3 crossref_primary_10_1016_j_compag_2023_107862 crossref_primary_10_1016_j_ecoinf_2023_102193 crossref_primary_10_3390_rs13183613 crossref_primary_10_3390_agriculture13122182 crossref_primary_10_1016_j_procs_2018_05_198 crossref_primary_10_3390_s22176354 crossref_primary_10_1145_3715093 crossref_primary_10_1038_s41598_022_07034_5 crossref_primary_10_1063_10_0003218 crossref_primary_10_1016_j_cviu_2024_104102 crossref_primary_10_1088_2632_2153_acc638 crossref_primary_10_3390_s24051509 crossref_primary_10_3390_rs15215238 crossref_primary_10_3390_app12104912 crossref_primary_10_3390_app14020864 crossref_primary_10_1002_adts_202200140 crossref_primary_10_1007_s00530_025_01705_9 crossref_primary_10_1007_s11042_022_13831_x crossref_primary_10_3390_rs12203372 crossref_primary_10_1109_TGRS_2020_2990640 crossref_primary_10_3390_rs17030411 crossref_primary_10_1177_14759217231168212 crossref_primary_10_1038_s41598_024_55864_2 crossref_primary_10_1007_s11356_022_22167_w crossref_primary_10_1007_s12559_024_10257_5 crossref_primary_10_3390_electronics12122669 crossref_primary_10_3390_app122010316 crossref_primary_10_3390_rs13061176 crossref_primary_10_1016_j_patcog_2020_107333 crossref_primary_10_3390_s24175552 crossref_primary_10_1016_j_compstruct_2023_116672 crossref_primary_10_3390_s20030717 crossref_primary_10_3390_electronics9111768 crossref_primary_10_1007_s11004_023_10108_3 crossref_primary_10_1080_15583058_2023_2260771 crossref_primary_10_3390_app10217524 crossref_primary_10_3390_rs15215218 crossref_primary_10_1109_JBHI_2020_3045475 crossref_primary_10_1007_s10462_022_10152_1 crossref_primary_10_1038_s41598_022_13878_8 crossref_primary_10_3390_s20205759 crossref_primary_10_1109_TITS_2021_3076844 crossref_primary_10_1109_ACCESS_2024_3389979 crossref_primary_10_1186_s13007_023_01031_z crossref_primary_10_3390_app14020603 crossref_primary_10_3390_rs12101574 crossref_primary_10_3390_app11146524 crossref_primary_10_7717_peerj_cs_1453 crossref_primary_10_1007_s10489_024_05406_0 crossref_primary_10_3390_math10234468 crossref_primary_10_3390_electronics10161932 crossref_primary_10_3390_s21113813 crossref_primary_10_1080_13682199_2022_2163531 crossref_primary_10_3390_app11020518 crossref_primary_10_3390_min11111265 crossref_primary_10_3390_ijgi10030168 crossref_primary_10_3390_jmse6030093 crossref_primary_10_1007_s11063_021_10704_6 crossref_primary_10_3390_rs15051212 crossref_primary_10_1109_JSTARS_2024_3351873 crossref_primary_10_1007_s10462_022_10176_7 crossref_primary_10_3390_bdcc5010009 crossref_primary_10_1016_j_asoc_2020_106698 crossref_primary_10_1155_2021_3846078 crossref_primary_10_1002_gj_4615 crossref_primary_10_1093_bioinformatics_btae559 crossref_primary_10_3390_rs14236049 crossref_primary_10_1093_iob_obae036 crossref_primary_10_3390_rs14133046 crossref_primary_10_1016_j_inpa_2022_05_002 crossref_primary_10_1109_ACCESS_2021_3133712 crossref_primary_10_1007_s43762_021_00031_w crossref_primary_10_1016_j_dss_2022_113794 crossref_primary_10_3390_land12040810 crossref_primary_10_1016_j_asoc_2023_110315 crossref_primary_10_1016_j_bspc_2022_103978 crossref_primary_10_1016_j_isprsjprs_2021_11_010 crossref_primary_10_1109_ACCESS_2023_3318486 crossref_primary_10_1002_rob_22248 crossref_primary_10_1051_wujns_2023282150 crossref_primary_10_3390_app14041527 crossref_primary_10_1016_j_neucom_2022_01_022 crossref_primary_10_1038_s41699_020_0137_z crossref_primary_10_3390_s22062416 crossref_primary_10_61186_jgit_11_3_43 crossref_primary_10_1016_j_csbj_2020_08_003 crossref_primary_10_1016_j_eswa_2022_118815 crossref_primary_10_3390_app11041807 crossref_primary_10_1016_j_asoc_2020_106210 crossref_primary_10_3390_s21041196 crossref_primary_10_1007_s11082_023_06249_8 crossref_primary_10_3390_app14062455 crossref_primary_10_3390_electronics13122366 crossref_primary_10_1109_ACCESS_2021_3086530 crossref_primary_10_1002_mrm_27550 crossref_primary_10_1016_j_neucom_2024_127509 crossref_primary_10_31127_tuje_1481696 crossref_primary_10_1177_14759217221126170 crossref_primary_10_1016_j_dsp_2021_103134 crossref_primary_10_1007_s11042_022_12842_y crossref_primary_10_1016_j_eswa_2021_115486 crossref_primary_10_1016_j_jag_2023_103421 crossref_primary_10_3390_jimaging6090085 crossref_primary_10_3390_rs14010223 crossref_primary_10_3390_rs14010228 crossref_primary_10_1007_s11042_020_09187_9 crossref_primary_10_1002_jsid_2018 crossref_primary_10_1038_s44172_023_00066_3 crossref_primary_10_3390_ma17194819 crossref_primary_10_1155_2020_2785464 crossref_primary_10_1080_07391102_2022_2136244 crossref_primary_10_3390_rs14081848 crossref_primary_10_1007_s10489_021_02542_9 crossref_primary_10_1109_JSTARS_2022_3181355 crossref_primary_10_1016_j_bspc_2021_103472 crossref_primary_10_1016_j_isprsjprs_2020_08_001 crossref_primary_10_1016_j_bspc_2022_103532 crossref_primary_10_1016_j_ecoinf_2023_102116 crossref_primary_10_1007_s00371_024_03266_w crossref_primary_10_1109_ACCESS_2019_2958671 crossref_primary_10_1007_s00371_022_02734_5 crossref_primary_10_1007_s10668_022_02740_6 crossref_primary_10_1016_j_asoc_2019_105820 crossref_primary_10_3390_drones9030221 crossref_primary_10_1016_j_conbuildmat_2023_132839 crossref_primary_10_1016_j_cmpb_2019_105273 crossref_primary_10_3390_rs17060974 crossref_primary_10_3390_cancers14051199 crossref_primary_10_3390_electronics11081241 crossref_primary_10_3390_s22218086 crossref_primary_10_1016_j_engappai_2024_109683 crossref_primary_10_1016_j_eswa_2021_115064 crossref_primary_10_3390_rs15245694 crossref_primary_10_1016_j_matdes_2024_113031 crossref_primary_10_3390_s20236711 crossref_primary_10_1016_j_dib_2019_104414 crossref_primary_10_3390_agriculture13071283 crossref_primary_10_3390_rs15112800 crossref_primary_10_3390_ijgi13100347 crossref_primary_10_3390_rs13091828 crossref_primary_10_12677_CSA_2023_134081 crossref_primary_10_1016_j_measurement_2023_112499 crossref_primary_10_1016_j_energy_2018_09_118 crossref_primary_10_1007_s11831_022_09811_x crossref_primary_10_1038_s41598_020_78632_4 crossref_primary_10_3390_sym12030427 crossref_primary_10_1109_ACCESS_2020_3001679 crossref_primary_10_1016_j_watres_2021_117482 crossref_primary_10_1109_ACCESS_2021_3085218 crossref_primary_10_1038_s41598_019_53254_7 crossref_primary_10_3390_agronomy12112812 crossref_primary_10_3390_jpm11070629 crossref_primary_10_1016_j_ultras_2024_107358 crossref_primary_10_1088_1361_6501_ac0216 crossref_primary_10_3390_s19143106 crossref_primary_10_1007_s42044_021_00090_6 crossref_primary_10_2139_ssrn_4109973 crossref_primary_10_3390_rs13163122 crossref_primary_10_3389_fonc_2023_1009681 crossref_primary_10_3390_app11030968 crossref_primary_10_1016_j_jag_2023_103624 crossref_primary_10_4236_jcc_2024_129011 crossref_primary_10_3390_rs13245043 crossref_primary_10_3390_rs16234583 crossref_primary_10_1109_TPAMI_2020_3045007 crossref_primary_10_1002_ima_23129 crossref_primary_10_1080_08839514_2022_2039348 crossref_primary_10_1016_j_rineng_2024_103383 crossref_primary_10_1016_j_asoc_2023_111224 crossref_primary_10_1016_j_eswa_2021_116105 crossref_primary_10_31590_ejosat_779059 crossref_primary_10_2208_jscejhe_76_2_I_997 crossref_primary_10_1007_s00521_023_08839_9 crossref_primary_10_31857_S1234567823190072 crossref_primary_10_1016_j_asoc_2019_105612 crossref_primary_10_1109_TPAMI_2022_3225573 crossref_primary_10_1016_j_compag_2024_108702 crossref_primary_10_3390_rs13071234 crossref_primary_10_1080_10095020_2024_2343323 crossref_primary_10_3390_math8050768 crossref_primary_10_3390_diagnostics10080577 crossref_primary_10_1093_gigascience_giab052 crossref_primary_10_3390_rs13224597 crossref_primary_10_1109_TCSVT_2024_3495769 crossref_primary_10_1109_ACCESS_2020_3001652 crossref_primary_10_1016_j_undsp_2024_10_002 crossref_primary_10_1080_10402004_2022_2037800 crossref_primary_10_3390_s24061804 crossref_primary_10_1155_2021_5596135 crossref_primary_10_1007_s11082_020_02500_8 crossref_primary_10_1109_LRA_2022_3187836 crossref_primary_10_3390_photonics10010011 crossref_primary_10_4018_JITR_299932 crossref_primary_10_3390_jimaging8090244 crossref_primary_10_1016_j_patrec_2021_10_009 crossref_primary_10_3390_rs10060973 crossref_primary_10_1109_ACCESS_2021_3124831 crossref_primary_10_12677_AAM_2022_116403 crossref_primary_10_1007_s11042_022_13606_4 crossref_primary_10_3390_jmse11040691 crossref_primary_10_1007_s00371_021_02324_x crossref_primary_10_1007_s11042_023_15201_7 crossref_primary_10_1007_s10462_019_09792_7 crossref_primary_10_1371_journal_pone_0227677 crossref_primary_10_1016_j_lwt_2023_115047 crossref_primary_10_1007_s11063_024_11533_z crossref_primary_10_1155_2022_6010912 crossref_primary_10_1007_s10980_021_01303_w crossref_primary_10_3390_s22062252 crossref_primary_10_3390_e23020197 crossref_primary_10_3390_app10031183 crossref_primary_10_1016_j_compag_2023_108051 crossref_primary_10_1016_j_scitotenv_2019_134413 crossref_primary_10_3390_app8040500 crossref_primary_10_1016_j_bspc_2022_103907 crossref_primary_10_1016_j_eswa_2021_115090 crossref_primary_10_1016_j_neucom_2021_08_009 crossref_primary_10_3103_S8756699019020109 crossref_primary_10_1002_nbm_4609 crossref_primary_10_1016_j_marpolbul_2022_113343 crossref_primary_10_1049_iet_ipr_2018_6582 crossref_primary_10_1109_ACCESS_2022_3192605 crossref_primary_10_1145_3524497 crossref_primary_10_3390_rs12060934 crossref_primary_10_1109_ACCESS_2019_2958825 crossref_primary_10_3390_app11198802 crossref_primary_10_3390_rs12091435 crossref_primary_10_1016_j_cageo_2021_104778 crossref_primary_10_3390_rs13234759 crossref_primary_10_3390_rs13142656 crossref_primary_10_1007_s00371_020_01981_8 crossref_primary_10_3390_ijgi8120582 crossref_primary_10_1007_s40747_024_01364_9 crossref_primary_10_1016_j_compag_2023_108029 crossref_primary_10_3390_s21238047 crossref_primary_10_1016_j_mineng_2022_107806 crossref_primary_10_1016_j_comcom_2022_10_011 crossref_primary_10_3390_rs12060944 crossref_primary_10_3390_rs14174225 crossref_primary_10_1016_j_procir_2023_09_172 crossref_primary_10_3390_app14209521 crossref_primary_10_1109_TIP_2021_3109530 crossref_primary_10_31590_ejosat_1115837 crossref_primary_10_1016_j_aei_2024_102586 crossref_primary_10_1080_10298436_2024_2400562 crossref_primary_10_1109_TIP_2023_3319274 crossref_primary_10_37391_ijeer_110443 crossref_primary_10_1007_s00521_023_08961_8 crossref_primary_10_1109_JSTARS_2025_3538920 crossref_primary_10_3390_s24113421 crossref_primary_10_3390_land13081161 crossref_primary_10_1109_LRA_2022_3143219 crossref_primary_10_1111_mice_12792 crossref_primary_10_1016_j_ufug_2023_127845 crossref_primary_10_1155_2022_8165580 crossref_primary_10_3390_rs12060959 crossref_primary_10_3390_rs16173327 crossref_primary_10_1109_TMM_2021_3080516 crossref_primary_10_3390_tomography8040156 crossref_primary_10_2174_1573405616666210108122048 crossref_primary_10_3390_electronics10010081 crossref_primary_10_1016_j_ins_2020_11_048 crossref_primary_10_1016_j_engstruct_2023_117219 crossref_primary_10_1038_s41598_022_16978_7 crossref_primary_10_3390_electronics10172046 crossref_primary_10_1016_j_bbe_2020_01_004 crossref_primary_10_1111_phor_12531 crossref_primary_10_3390_agronomy13061469 crossref_primary_10_3390_rs13010039 crossref_primary_10_1016_j_cmpb_2023_107914 crossref_primary_10_1016_j_cviu_2023_103886 crossref_primary_10_1038_s41598_024_79919_6 crossref_primary_10_1007_s11042_023_17113_y crossref_primary_10_1155_2022_8342767 crossref_primary_10_1016_j_jsb_2019_107432 crossref_primary_10_1007_s13735_020_00195_x crossref_primary_10_1109_ACCESS_2020_3006919 crossref_primary_10_3390_plants12040786 crossref_primary_10_3390_rs13010026 crossref_primary_10_1080_00207543_2020_1859636 crossref_primary_10_11728_cjss2021_04_667 crossref_primary_10_1016_j_epsr_2022_108148 crossref_primary_10_1111_exsy_12826 crossref_primary_10_3390_diagnostics13121994 crossref_primary_10_2139_ssrn_4015024 crossref_primary_10_3390_rs11010068 crossref_primary_10_1016_j_neunet_2019_07_020 crossref_primary_10_3390_rs12223685 crossref_primary_10_3390_rs10081215 crossref_primary_10_1016_j_inpa_2020_01_002 crossref_primary_10_1002_mrm_27758 crossref_primary_10_1007_s10278_024_01142_6 crossref_primary_10_3390_f10030235 crossref_primary_10_1109_ACCESS_2020_3023495 crossref_primary_10_3390_f15040689 crossref_primary_10_1049_ipr2_12824 crossref_primary_10_1016_j_geomorph_2024_109212 crossref_primary_10_1016_j_cogr_2021_06_003 crossref_primary_10_1039_D2NA00781A crossref_primary_10_3390_land13111842 crossref_primary_10_1016_j_patcog_2021_108023 crossref_primary_10_3390_agriculture12091493 crossref_primary_10_1016_j_infrared_2021_103883 crossref_primary_10_1016_j_eswa_2022_117106 crossref_primary_10_1007_s00521_023_08214_8 crossref_primary_10_1109_TCYB_2021_3065247 crossref_primary_10_1007_s40747_023_01103_6 crossref_primary_10_1016_j_compag_2020_105302 crossref_primary_10_3390_rs13081420 crossref_primary_10_3390_su141912321 crossref_primary_10_1007_s12652_022_03736_w crossref_primary_10_3390_rs14040897 crossref_primary_10_1007_s10015_022_00827_x crossref_primary_10_1016_j_cviu_2019_07_005 crossref_primary_10_1109_JSAC_2022_3221950 crossref_primary_10_3390_rs14122826 crossref_primary_10_1007_s13349_024_00879_6 crossref_primary_10_1016_j_imu_2020_100297 crossref_primary_10_1109_ACCESS_2025_3526244 crossref_primary_10_3390_rs13010119 crossref_primary_10_4018_IJSST_2019010101 crossref_primary_10_1038_s41524_023_01172_8 crossref_primary_10_3390_s24020522 crossref_primary_10_1109_MGRS_2023_3292467 crossref_primary_10_1016_j_geoderma_2019_113977 crossref_primary_10_1111_mice_13052 crossref_primary_10_1007_s10462_021_10018_y crossref_primary_10_1016_j_neunet_2022_10_006 crossref_primary_10_1021_acsnano_0c09685 crossref_primary_10_1051_matecconf_202236405020 crossref_primary_10_1111_exsy_13663 crossref_primary_10_3390_app10186473 crossref_primary_10_1155_2018_8207201 crossref_primary_10_1016_j_isprsjprs_2021_06_002 crossref_primary_10_3390_rs13112140 crossref_primary_10_1515_cdbme_2020_0034 crossref_primary_10_3390_f13111813 crossref_primary_10_1016_j_future_2018_02_036 crossref_primary_10_1016_j_media_2024_103179 crossref_primary_10_3390_s24020510 crossref_primary_10_3390_app10207272 crossref_primary_10_3390_app8050837 crossref_primary_10_1016_j_cities_2022_103834 crossref_primary_10_3390_rs13183595 crossref_primary_10_3390_app9153128 crossref_primary_10_3390_computers8040072 crossref_primary_10_1007_s11063_022_10864_z crossref_primary_10_1016_j_engappai_2024_108602 crossref_primary_10_3390_app10072471 crossref_primary_10_1007_s00521_024_09660_8 crossref_primary_10_1016_j_cose_2022_102632 crossref_primary_10_1016_j_jag_2021_102411 crossref_primary_10_1038_s41598_022_05455_w crossref_primary_10_3390_s21051570 crossref_primary_10_1515_teme_2021_0028 crossref_primary_10_1680_jgeot_20_P_091 crossref_primary_10_1007_s00521_023_08758_9 crossref_primary_10_3390_s19194329 crossref_primary_10_1016_j_asoc_2024_112315 crossref_primary_10_1016_j_bspc_2021_102825 crossref_primary_10_3390_electronics10101187 crossref_primary_10_4329_wjr_v12_i1_1 crossref_primary_10_1016_j_rse_2022_113203 crossref_primary_10_12677_JISP_2023_121007 crossref_primary_10_4108_eetiot_4590 crossref_primary_10_3390_mi14010053 crossref_primary_10_1109_ACCESS_2022_3166603 crossref_primary_10_1007_s11227_022_04642_w crossref_primary_10_1016_j_rcim_2023_102574 crossref_primary_10_3390_rs10101553 crossref_primary_10_1109_TCSVT_2024_3431714 crossref_primary_10_1016_j_engappai_2023_107449 crossref_primary_10_1016_j_displa_2022_102223 crossref_primary_10_3390_s24020531 crossref_primary_10_1007_s10846_021_01395_1 crossref_primary_10_1016_j_eswa_2020_114417 crossref_primary_10_3390_rs11182142 crossref_primary_10_1007_s12541_023_00937_x crossref_primary_10_3390_app8122393 crossref_primary_10_1007_s00170_022_09791_z crossref_primary_10_3390_foods11193150 crossref_primary_10_3390_jpm11040310 crossref_primary_10_1109_ACCESS_2022_3147251 crossref_primary_10_1145_3480970 crossref_primary_10_1049_iet_ipr_2020_0491 crossref_primary_10_3390_s25020370 crossref_primary_10_1177_15589250231168950 crossref_primary_10_3390_app11031127 crossref_primary_10_3390_geosciences8070244 crossref_primary_10_1007_s12145_024_01654_3 crossref_primary_10_1016_j_isprsjprs_2022_02_002 crossref_primary_10_1016_j_coal_2025_104712 crossref_primary_10_3390_rs10091429 crossref_primary_10_1007_s11042_022_14303_y crossref_primary_10_2208_jscejhe_77_2_I_901 crossref_primary_10_3390_app122211799 crossref_primary_10_3390_rs14143324 crossref_primary_10_1007_s10853_020_05148_7 crossref_primary_10_1007_s11661_020_06008_4 crossref_primary_10_1109_TMM_2024_3357198 crossref_primary_10_1186_s12859_020_03943_2 crossref_primary_10_1007_s00500_020_05045_w crossref_primary_10_1007_s00371_023_03161_w crossref_primary_10_1016_j_aei_2020_101169 crossref_primary_10_3390_s21072272 crossref_primary_10_1016_j_cja_2020_09_024 crossref_primary_10_3390_rs16142561 crossref_primary_10_3390_s22134696 crossref_primary_10_1186_s42400_023_00141_4 crossref_primary_10_3390_electronics11121884 crossref_primary_10_3390_rs10091423 crossref_primary_10_37394_23205_2024_23_25 crossref_primary_10_1111_mice_13233 crossref_primary_10_1016_j_micpro_2023_104830 crossref_primary_10_1016_j_measurement_2022_111566 crossref_primary_10_3390_electronics12102339 crossref_primary_10_1016_j_neucom_2023_126609 crossref_primary_10_1038_s41598_025_89952_8 crossref_primary_10_3390_s24072134 crossref_primary_10_1016_j_compag_2020_105947 crossref_primary_10_1007_s12652_023_04607_8 crossref_primary_10_3390_land14030649 crossref_primary_10_1155_2022_9541115 crossref_primary_10_3390_s21237947 crossref_primary_10_1016_j_cj_2021_05_014 crossref_primary_10_3390_en14102960 crossref_primary_10_1109_TGRS_2023_3264232 crossref_primary_10_1007_s10489_022_03774_z crossref_primary_10_34133_plantphenomics_0064 crossref_primary_10_1007_s11042_021_11643_z crossref_primary_10_3390_s19194188 crossref_primary_10_1007_s11701_023_01657_0 crossref_primary_10_3390_app15020871 crossref_primary_10_3390_app11199119 crossref_primary_10_1115_1_4063983 crossref_primary_10_3390_met13081395 crossref_primary_10_1016_j_rinp_2022_105904 crossref_primary_10_1109_LRA_2018_2849498 crossref_primary_10_3389_fnins_2020_586197 crossref_primary_10_1007_s00500_022_07138_0 crossref_primary_10_1016_j_sna_2024_115394 crossref_primary_10_3390_s23156753 crossref_primary_10_1007_s12559_017_9530_0 crossref_primary_10_3390_rs14143370 crossref_primary_10_3390_jpm12020309 crossref_primary_10_3390_w15244202 crossref_primary_10_1007_s10278_021_00452_3 crossref_primary_10_3390_su141912178 crossref_primary_10_1088_2632_2153_aba8e8 crossref_primary_10_17798_bitlisfen_1432965 crossref_primary_10_3390_s20164430 crossref_primary_10_3390_rs16111854 crossref_primary_10_3390_s23249839 crossref_primary_10_3390_bioengineering10091060 crossref_primary_10_3390_rs12101667 crossref_primary_10_1080_21681163_2024_2373996 crossref_primary_10_3390_ijerph19031272 crossref_primary_10_3390_s20154161 crossref_primary_10_1364_BOE_449714 crossref_primary_10_1080_26895293_2024_2399683 crossref_primary_10_1016_j_jag_2021_102497 crossref_primary_10_1016_j_jvir_2024_06_028 crossref_primary_10_7717_peerj_cs_773 crossref_primary_10_3390_s23062936 crossref_primary_10_7717_peerj_cs_1770 crossref_primary_10_1073_pnas_1916219117 crossref_primary_10_1088_2051_672X_ac9492 crossref_primary_10_1109_LRA_2022_3180439 crossref_primary_10_1080_17538947_2024_2418880 crossref_primary_10_3390_rs17061019 crossref_primary_10_3390_s21051720 crossref_primary_10_1016_j_neunet_2019_04_024 crossref_primary_10_3390_rs15215148 crossref_primary_10_1016_j_procs_2018_01_104 crossref_primary_10_1016_j_ifacol_2020_12_696 crossref_primary_10_1002_stc_2981 crossref_primary_10_3390_wevj15110516 crossref_primary_10_1007_s11760_019_01589_z crossref_primary_10_3390_app12199691 crossref_primary_10_3800_pbr_17_91 crossref_primary_10_1109_JSTARS_2022_3178470 crossref_primary_10_1088_1757_899X_1022_1_012118 crossref_primary_10_1038_s41598_022_11842_0 crossref_primary_10_1109_ACCESS_2020_3011406 crossref_primary_10_1002_ppj2_20065 crossref_primary_10_1016_j_triboint_2022_107948 crossref_primary_10_3390_biom10121691 crossref_primary_10_1049_ipr2_13101 crossref_primary_10_3390_f12060768 crossref_primary_10_1038_s41598_019_56649_8 crossref_primary_10_1109_TGRS_2023_3240481 crossref_primary_10_1016_j_compmedimag_2024_102396 crossref_primary_10_3788_LOP232714 crossref_primary_10_1038_s41586_023_06174_6 crossref_primary_10_1109_LRA_2021_3061359 crossref_primary_10_3390_machines10040285 crossref_primary_10_1007_s11517_023_02963_3 crossref_primary_10_1007_s11042_023_16806_8 crossref_primary_10_3390_rs14246291 crossref_primary_10_1016_j_engfailanal_2021_105268 crossref_primary_10_1016_j_geoen_2023_212529 crossref_primary_10_3390_rs14246297 crossref_primary_10_1007_s11053_021_09896_4 crossref_primary_10_1016_j_ijmecsci_2022_107529 crossref_primary_10_3390_s20216305 crossref_primary_10_3390_foods12030624 crossref_primary_10_1016_j_compag_2021_106226 crossref_primary_10_3390_diagnostics12020557 crossref_primary_10_3390_rs13214370 crossref_primary_10_1007_s11042_023_14958_1 crossref_primary_10_1364_BOE_385218 crossref_primary_10_1038_s41598_023_29230_7 crossref_primary_10_3390_electronics12061347 crossref_primary_10_3390_rs12020311 crossref_primary_10_1016_j_visinf_2024_11_002 crossref_primary_10_3390_jimaging8100284 crossref_primary_10_1080_21681163_2020_1790040 crossref_primary_10_3390_app12073247 crossref_primary_10_1016_j_energy_2022_124933 crossref_primary_10_53469_jssh_2024_6_12__20 crossref_primary_10_1109_ACCESS_2023_3321912 crossref_primary_10_3390_polym15020295 crossref_primary_10_1016_j_asoc_2020_106874 crossref_primary_10_3390_rs14133109 crossref_primary_10_1038_s41598_023_31677_7 crossref_primary_10_1016_j_compag_2021_106482 crossref_primary_10_1007_s11042_023_16782_z crossref_primary_10_1016_j_patcog_2019_107125 crossref_primary_10_1016_j_engfracmech_2024_110149 crossref_primary_10_3390_rs12030560 crossref_primary_10_1016_j_compstruc_2021_106570 crossref_primary_10_1177_00220345241226871 crossref_primary_10_1007_s13278_024_01362_2 crossref_primary_10_3390_rs12132159 crossref_primary_10_1016_j_comcom_2021_06_022 crossref_primary_10_1016_j_media_2021_101994 crossref_primary_10_3390_app12125960 crossref_primary_10_32604_cmc_2022_028632 crossref_primary_10_1007_s12517_021_08420_5 crossref_primary_10_1007_s11694_020_00707_7 crossref_primary_10_3390_ijerph15081576 crossref_primary_10_1016_j_undsp_2023_09_012 crossref_primary_10_2139_ssrn_4158164 crossref_primary_10_3390_s22249743 crossref_primary_10_1016_j_eswa_2022_116812 crossref_primary_10_3390_electronics14030620 crossref_primary_10_1109_ACCESS_2022_3184453 crossref_primary_10_1007_s11831_021_09542_5 crossref_primary_10_3390_bioengineering11100994 crossref_primary_10_3390_land11060905 crossref_primary_10_3390_s19245361 crossref_primary_10_3390_s22197131 crossref_primary_10_3390_electronics12122730 crossref_primary_10_3390_f15091504 crossref_primary_10_3390_mi13111920 crossref_primary_10_1080_01431161_2024_2365811 crossref_primary_10_1007_s40747_023_01054_y crossref_primary_10_1016_j_jmr_2025_107851 crossref_primary_10_35414_akufemubid_1013047 crossref_primary_10_1007_s11814_024_00277_0 crossref_primary_10_3390_rs12162532 crossref_primary_10_3390_rs16122222 crossref_primary_10_3390_s21082627 crossref_primary_10_1007_s11517_024_03252_3 crossref_primary_10_1016_j_engstruct_2024_118996 crossref_primary_10_1186_s40543_023_00407_z crossref_primary_10_1016_j_autcon_2022_104342 crossref_primary_10_1007_s44163_021_00004_2 crossref_primary_10_3390_s22176546 crossref_primary_10_1016_j_eswa_2022_117846 crossref_primary_10_1016_j_ijpharm_2022_122179 crossref_primary_10_1016_j_tust_2020_103677 crossref_primary_10_3390_jimaging8030055 crossref_primary_10_1002_rob_22120 crossref_primary_10_1016_j_compag_2021_105987 crossref_primary_10_2196_63686 crossref_primary_10_1016_j_neucom_2022_11_084 crossref_primary_10_1016_j_aej_2023_04_062 crossref_primary_10_1002_esp_5652 crossref_primary_10_3390_app122211801 crossref_primary_10_3390_jmse11071265 crossref_primary_10_1016_j_ymssp_2022_109287 crossref_primary_10_1016_j_neucom_2020_06_095 crossref_primary_10_1016_j_isprsjprs_2018_04_022 crossref_primary_10_1016_j_bspc_2022_103633 crossref_primary_10_37394_232015_2020_16_65 crossref_primary_10_1097_ACM_0000000000003630 crossref_primary_10_3390_e24070942 crossref_primary_10_3390_app10134486 crossref_primary_10_1016_j_future_2021_06_045 crossref_primary_10_1016_j_cviu_2023_103744 crossref_primary_10_1016_j_compbiomed_2020_103738 crossref_primary_10_1016_j_compchemeng_2021_107614 crossref_primary_10_1186_s40494_023_00895_7 crossref_primary_10_1016_j_isprsjprs_2023_07_024 crossref_primary_10_1016_j_tust_2023_105107 crossref_primary_10_1016_j_measurement_2023_113207 crossref_primary_10_1007_s11042_023_17112_z crossref_primary_10_1016_j_measurement_2023_113205 crossref_primary_10_1007_s00521_021_06401_z crossref_primary_10_3390_rs16132276 crossref_primary_10_1109_ACCESS_2023_3241638 crossref_primary_10_1093_jge_gxad024 crossref_primary_10_1117_1_JBO_28_10_106003 crossref_primary_10_1190_geo2018_0870_1 crossref_primary_10_1109_LGRS_2023_3333017 crossref_primary_10_1016_j_neucom_2019_02_003 crossref_primary_10_1186_s12859_024_05894_4 crossref_primary_10_3390_rs14194763 crossref_primary_10_3390_ijgi13050153 crossref_primary_10_3390_app112412093 crossref_primary_10_1088_1361_6501_ac3856 crossref_primary_10_1007_s11042_023_14978_x crossref_primary_10_1016_j_egyai_2023_100265 crossref_primary_10_5194_essd_14_295_2022 crossref_primary_10_1016_j_asoc_2021_107511 crossref_primary_10_3390_electronics12132975 crossref_primary_10_1016_j_imavis_2023_104708 crossref_primary_10_1016_j_compag_2019_105091 crossref_primary_10_3390_computers9040099 crossref_primary_10_1038_s41598_023_29665_y crossref_primary_10_1109_TMLCN_2025_3530875 crossref_primary_10_4028_p_6bfVRH crossref_primary_10_3390_rs14194744 crossref_primary_10_1088_1742_6596_2356_1_012039 crossref_primary_10_1038_s41598_023_32149_8 crossref_primary_10_3389_fcvm_2020_00086 crossref_primary_10_1016_j_neucom_2023_03_006 crossref_primary_10_3390_rs11070847 crossref_primary_10_1007_s41064_020_00124_x crossref_primary_10_1002_mp_14512 crossref_primary_10_1016_j_petrol_2022_110734 crossref_primary_10_3390_rs11242912 crossref_primary_10_1007_s00138_023_01391_5 crossref_primary_10_1016_j_imavis_2022_104401 crossref_primary_10_3390_s21196565 crossref_primary_10_1016_j_asoc_2019_105975 crossref_primary_10_1007_s10462_020_09854_1 crossref_primary_10_3390_rs12172770 crossref_primary_10_1007_s00521_024_10165_7 crossref_primary_10_1007_s42979_023_02338_3 crossref_primary_10_1109_MSP_2020_2977269 crossref_primary_10_1109_TIV_2020_2980671 crossref_primary_10_3390_rs15082208 crossref_primary_10_1109_ACCESS_2023_3241837 crossref_primary_10_3390_rs15061525 crossref_primary_10_1038_s41598_020_78799_w crossref_primary_10_1080_10095020_2023_2292587 crossref_primary_10_1016_j_asoc_2020_106353 crossref_primary_10_1145_3472770 crossref_primary_10_17341_gazimmfd_652101 crossref_primary_10_3390_jimaging7110241 crossref_primary_10_1016_j_energy_2019_03_080 crossref_primary_10_1017_S0890060420000372 crossref_primary_10_1016_j_patcog_2023_109667 crossref_primary_10_1088_1361_6501_aceb7e crossref_primary_10_1002_jbio_202300078 crossref_primary_10_1016_j_aei_2021_101307 crossref_primary_10_1109_JIOT_2020_3022353 crossref_primary_10_1088_1742_6596_2418_1_012081 crossref_primary_10_1016_j_compchemeng_2022_107768 crossref_primary_10_1016_j_bbe_2020_09_008 crossref_primary_10_1016_j_ecolind_2024_111844 crossref_primary_10_1007_s00530_021_00758_w crossref_primary_10_21307_ijanmc_2021_022 crossref_primary_10_3390_pharmaceutics14112257 crossref_primary_10_34133_research_0491 crossref_primary_10_1111_mice_12481 crossref_primary_10_1134_S1054661821030202 crossref_primary_10_1049_iet_ipr_2019_1398 crossref_primary_10_3390_electronics12040827 crossref_primary_10_3390_rs14061516 crossref_primary_10_3390_s23136238 crossref_primary_10_1088_2399_6528_abebcf crossref_primary_10_3390_s20020563 crossref_primary_10_3390_s21062153 crossref_primary_10_3389_frai_2020_00072 crossref_primary_10_1016_j_cviu_2020_103077 crossref_primary_10_3390_rs16050817 crossref_primary_10_3390_electronics12194169 crossref_primary_10_1007_s41870_023_01408_2 crossref_primary_10_1080_13621718_2019_1687635 crossref_primary_10_1111_exsy_12742 crossref_primary_10_3390_app15031063 crossref_primary_10_1134_S0021364023602725 crossref_primary_10_1155_2021_3481469 crossref_primary_10_34133_plantphenomics_0271 crossref_primary_10_1038_s41598_024_64636_x crossref_primary_10_1007_s10278_018_0160_1 crossref_primary_10_3390_rs12152368 crossref_primary_10_3390_rs14071527 crossref_primary_10_1016_j_neucom_2021_08_157 crossref_primary_10_3390_land13071007 crossref_primary_10_1007_s00500_024_09946_y crossref_primary_10_1007_s11604_018_0795_3 crossref_primary_10_1007_s12021_021_09556_1 crossref_primary_10_1109_TGRS_2024_3446628 crossref_primary_10_1007_s44379_024_00003_x crossref_primary_10_1007_s44196_023_00364_w crossref_primary_10_1016_j_bspc_2021_102661 crossref_primary_10_1016_j_media_2018_08_007 crossref_primary_10_1007_s11554_021_01170_3 crossref_primary_10_1007_s10494_020_00151_z crossref_primary_10_1016_j_asoc_2020_106153 crossref_primary_10_3390_s21103389 crossref_primary_10_1080_01431161_2021_1913298 crossref_primary_10_1109_TITS_2023_3321309 crossref_primary_10_1016_j_compag_2022_106911 crossref_primary_10_1186_s12859_020_3521_y crossref_primary_10_3390_s21041492 crossref_primary_10_1007_s11042_022_12447_5 crossref_primary_10_1007_s11042_022_12425_x crossref_primary_10_3390_app13010164 crossref_primary_10_1007_s12652_020_01803_8 crossref_primary_10_1016_j_isprsjprs_2024_02_010 crossref_primary_10_1007_s11042_023_14961_6 crossref_primary_10_1016_j_eswa_2023_119950 crossref_primary_10_1111_mice_12433 crossref_primary_10_3390_rs14153650 crossref_primary_10_3390_app14146298 crossref_primary_10_1061_JCEMD4_COENG_12542 crossref_primary_10_1109_ACCESS_2020_3045147 crossref_primary_10_1016_j_mlwa_2021_100158 crossref_primary_10_1109_TITS_2021_3127553 crossref_primary_10_3390_robotics10010002 crossref_primary_10_1016_j_marenvres_2022_105829 crossref_primary_10_3390_rs14163864 crossref_primary_10_1109_TMC_2023_3265010 crossref_primary_10_1007_s11760_021_01862_0 crossref_primary_10_1016_j_patrec_2020_10_011 crossref_primary_10_3390_app11209691 crossref_primary_10_1007_s41060_024_00660_4 crossref_primary_10_3390_f15030561 crossref_primary_10_1049_ipr2_12935 crossref_primary_10_3390_electronics11223787 crossref_primary_10_1016_j_cviu_2019_102809 crossref_primary_10_1016_j_isprsjprs_2021_07_012 crossref_primary_10_3390_f15030529 crossref_primary_10_1016_j_knosys_2024_112217 crossref_primary_10_1016_j_cmpb_2022_106874 crossref_primary_10_54569_aair_1164731 crossref_primary_10_1109_TIV_2023_3268051 crossref_primary_10_1155_are_8892810 crossref_primary_10_1186_s42400_023_00145_0 crossref_primary_10_3390_app9030404 crossref_primary_10_1016_j_engappai_2023_107486 crossref_primary_10_1016_j_measen_2023_100974 crossref_primary_10_1617_s11527_024_02341_x crossref_primary_10_3390_rs15184554 crossref_primary_10_3390_jmse10101503 crossref_primary_10_3390_w13182512 crossref_primary_10_1109_TIV_2022_3167733 crossref_primary_10_3390_app10082641 crossref_primary_10_4018_IJWLTT_334708 crossref_primary_10_1109_TIV_2022_3216734 crossref_primary_10_1080_14942119_2021_1831426 crossref_primary_10_3390_s25051278 crossref_primary_10_1109_JSTARS_2022_3203750 crossref_primary_10_1111_mice_12667 crossref_primary_10_2478_amns_2025_0338 crossref_primary_10_1016_j_cmpb_2021_106563 crossref_primary_10_29252_jgit_7_3_173 crossref_primary_10_1007_s11042_020_09518_w crossref_primary_10_3390_ma14216311 crossref_primary_10_1016_j_autcon_2021_103804 crossref_primary_10_3390_s22010329 crossref_primary_10_1016_j_conbuildmat_2024_138379 crossref_primary_10_1016_j_mlwa_2022_100422 crossref_primary_10_1016_j_procs_2019_02_076 crossref_primary_10_1111_cogs_13258 crossref_primary_10_1145_3714463 crossref_primary_10_1016_j_asoc_2021_107101 crossref_primary_10_1016_j_asoc_2021_107344 |
| Cites_doi | 10.1145/3005348 10.1162/neco.1997.9.8.1735 10.1109/CVPR.2012.6248074 10.1007/s11263-007-0090-8 10.1145/2461912.2462002 10.1007/s11263-007-0109-1 10.1007/s11263-015-0816-y 10.1177/0278364913491297 10.1109/ICCV.2013.458 10.1016/j.patrec.2008.04.005 10.1007/s11263-014-0733-5 10.1364/BOE.8.003627 10.1109/TIP.2005.852470 10.1145/2980179.2980238 10.1145/1531326.1531379 10.1016/j.jvcir.2015.10.012 10.1109/34.969114 10.1109/TPAMI.2012.231 10.1109/TPAMI.2016.2644615 |
| ContentType | Journal Article |
| Copyright | 2018 Elsevier B.V. |
| Copyright_xml | – notice: 2018 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2018.05.018 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-9681 |
| EndPage | 65 |
| ExternalDocumentID | 10_1016_j_asoc_2018_05_018 S1568494618302813 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~G- AATTM AAXKI AAYWO AAYXX ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c300t-f5249ac4f668f29ce130f9dfb5bb5e3fafc1a0def767655dac808412cf03e913 |
| IEDL.DBID | .~1 |
| ISSN | 1568-4946 |
| IngestDate | Tue Jul 01 01:50:01 EDT 2025 Thu Apr 24 23:02:06 EDT 2025 Fri Feb 23 02:45:59 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Semantic segmentation Scene labeling |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c300t-f5249ac4f668f29ce130f9dfb5bb5e3fafc1a0def767655dac808412cf03e913 |
| ORCID | 0000-0001-6817-6326 0000-0002-9575-6403 |
| PageCount | 25 |
| ParticipantIDs | crossref_primary_10_1016_j_asoc_2018_05_018 crossref_citationtrail_10_1016_j_asoc_2018_05_018 elsevier_sciencedirect_doi_10_1016_j_asoc_2018_05_018 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | September 2018 2018-09-00 |
| PublicationDateYYYYMMDD | 2018-09-01 |
| PublicationDate_xml | – month: 09 year: 2018 text: September 2018 |
| PublicationDecade | 2010 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2018 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Yosinski, Clune, Bengio, Lipson (bib0115) 2014 Shuai, Zuo, Wang, Wang (bib0435) 2016 Geiger, Lenz, Urtasun (bib0010) 2012 Gould, Fulton, Koller (bib0215) 2009 Farabet, Couprie, Najman, LeCun (bib0045) 2013; 35 Russell, Torralba, Murphy, Freeman (bib0310) 2008; 77 Ess, Müller, Grabner, Van Gool (bib0005) 2009 Krizhevsky, Sutskever, Hinton (bib0070) 2012 Raj, Maturana, Scherer (bib0385) 2015 Zheng, Jayasumana, Romera-Paredes, Vineet, Su, Du, Huang, Torr (bib0370) 2015 Roy, Conjeti, Karri, Sheet, Katouzian, Wachinger, Navab (bib0590) 2017; 8 Perazzi, Pont-Tuset, McWilliams, Van Gool, Gross, Sorkine-Hornung (bib0235) 2016 Byeon, Breuel, Raue, Liwicki (bib0425) 2015 Armeni, Sax, Zamir, Savarese (bib0270) 2017 Neverova, Luc, Couprie, Verbeek, LeCun (bib0485) 2017 Zeiler, Taylor, Fergus (bib0490) 2011 Quadros, Underwood, Douillard (bib0280) 2012 Brostow, Shotton, Fauqueur, Cipolla (bib0290) 2008 Shen, Hertzmann, Jia, Paris, Price, Shechtman, Sachs (bib0145) 2016; vol. 35 Zhang, Liu, Wang (bib0500) 2017 Zhang, Candra, Vetter, Zakhor (bib0210) 2015 Zhang, Jiang, Zhang, Li, Xia, Chen (bib0575) 2014 Gupta, Girshick, Arbeláez, Malik (bib0055) 2014 Krähenbühl, Koltun (bib0520) 2013 Yoon, Jeon, Yoo, Lee, So Kweon (bib0025) 2015 Cordts, Omran, Ramos, Rehfeld, Enzweiler, Benenson, Franke, Roth, Schiele (bib0015) 2016 Milletari, Navab, Ahmadi (bib0595) 2016 Tran, Bourdev, Fergus, Torresani, Paluri (bib0585) 2015 Ning, Delhomme, LeCun, Piano, Bottou, Barbano (bib0035) 2005; 14 Roy, Todorovic (bib0395) 2016 Pinheiro, Collobert, Dollar (bib0440) 2015 Richter, Vineet, Roth, Koltun (bib0135) 2016 Liang-Chieh, Papandreou, Kokkinos, Murphy, Yuille (bib0360) 2015 Shotton, Winn, Rother, Criminisi (bib0510) 2009; 81 Lin, Maire, Belongie, Hays, Perona, Ramanan, Dollár, Zitnick (bib0170) 2014 Ros, Sellart, Materzynska, Vazquez, Lopez (bib0175) 2016 Hackel, Wegner, Schindler (bib0285) 2016 Liu, Rabinovich, Berg (bib0405) 2015 Pont-Tuset, Perazzi, Caelles, Arbeláez, Sorkine-Hornung, Van Gool (bib0240) 2017 Zhao, Shi, Qi, Wang, Jia (bib0410) 2016 Chang, Funkhouser, Guibas, Hanrahan, Huang, Li, Savarese, Savva, Song, Su (bib0330) 2015 Eigen, Fergus (bib0390) 2015 Cordts, Omran, Ramos, Scharwächter, Enzweiler, Benenson, Franke, Roth, Schiele (bib0180) 2015 Boykov, Veksler, Zabih (bib0580) 2001; 23 Jain, Grauman (bib0225) 2014 Li, Gan, Liang, Yu, Cheng, Lin (bib0540) 2016 Mottaghi, Chen, Liu, Cho, Lee, Fidler, Urtasun, Yuille (bib0155) 2014 Xiao, Owens, Torralba (bib0250) 2013 Visin, Kastner, Cho, Matteucci, Courville, Bengio (bib0100) 2015 Chen, Mottaghi, Liu, Fidler, Urtasun, Yuille (bib0160) 2014 Chen, Golovinskiy, Funkhouser (bib0275) 2009; 28 Zagoruyko, Lerer, Lin, Pinheiro, Gross, Chintala, Dollár (bib0450) 2016 Ronneberger, Fischer, Brox (bib0345) 2015 Huang, You (bib0455) 2016 Ma, Stuckler, Kerl, Cremers (bib0565) 2017 Hariharan, Arbeláez, Bourdev, Maji, Malik (bib0165) 2011 Russakovsky, Deng, Su, Krause, Satheesh, Ma, Huang, Karpathy, Khosla, Bernstein (bib0130) 2015; 115 Prest, Leistner, Civera, Schmid, Ferrari (bib0300) 2012 Girshick, Donahue, Darrell, Malik (bib0555) 2014 Molchanov, Tyree, Karras, Aila, Kautz (bib0630) 2016 Wang, Sun, Liu, Sarma, Bronstein, Solomon (bib0470) 2018 Gupta, Arbelaez, Malik (bib0315) 2013 Zhu, Meng, Cai, Lu (bib0060) 2016; 34 Everingham, Eslami, Van Gool, Williams, Winn, Zisserman (bib0150) 2015; 111 Pinheiro, Lin, Collobert, Dollár (bib0445) 2016 Cho, van Merrienboer, Bahdanau, Bengio (bib0535) 2014 Long, Shelhamer, Darrell (bib0340) 2015 Zhou, Wu, Wu, Zhou (bib0525) 2015 Thoma (bib0065) 2016 Ros, Alvarez (bib0200) 2015 Pinheiro, Collobert (bib0430) 2014 Paszke, Chaurasia, Kim, Culurciello (bib0380) 2016 Arbeláez, Pont-Tuset, Barron, Marques, Malik (bib0550) 2014 Wan, Wang, Hoi, Wu, Zhu, Zhang, Li (bib0030) 2014 Li, Gan, Liang, Yu, Cheng, Lin (bib0420) 2016 Wong, Gatt, Stamatescu, McDonnell (bib0140) 2016 Szegedy, Liu, Jia, Sermanet, Reed, Anguelov, Erhan, Vanhoucke, Rabinovich (bib0085) 2015 Bell, Upchurch, Snavely, Bala (bib0230) 2015 Bell, Upchurch, Snavely, Bala (bib0305) 2013; 32 Pathak, Krähenbühl, Donahue, Darrell, Efros (bib0120) 2016 Song, Lichtenberg, Xiao (bib0255) 2015 Kendall, Badrinarayanan, Cipolla (bib0355) 2015 Noh, Hong, Han (bib0080) 2015 He, Zhang, Ren, Sun (bib0090) 2016 Alvarez, Gevers, LeCun, Lopez (bib0195) 2012 Liu, Yuen, Torralba (bib0220) 2009 Lai, Bo, Ren, Fox (bib0260) 2011 Bian, Lim, Zhou (bib0400) 2016 Yi, Kim, Ceylan, Shen, Yan, Su, Lu, Huang, Sheffer, Guibas (bib0265) 2016 Visin, Ciccone, Romero, Kastner, Cho, Bengio, Matteucci, Courville (bib0415) 2016 Han, Mao, Dally (bib0625) 2015 Brostow, Fauqueur, Cipolla (bib0185) 2009; 30 Ros, Ramos, Granados, Bakhtiary, Vazquez, Lopez (bib0205) 2015 Lin, Goyal, Girshick, He, Dollár (bib0600) 2017 Niepert, Ahmed, Kutzkov (bib0615) 2016 Qi, Su, Mo, Guibas (bib0460) 2016 Tran, Bourdev, Fergus, Torresani, Paluri (bib0480) 2016 Ciresan, Giusti, Gambardella, Schmidhuber (bib0040) 2012 Zeiler, Fergus (bib0495) 2014 Janoch, Karayev, Jia, Barron, Fritz, Saenko, Darrell (bib0320) 2013 Anwar, Hwang, Sung (bib0620) 2017; 13 Hariharan, Arbeláez, Girshick, Malik (bib0050) 2014 Simonyan, Zisserman (bib0075) 2014 Richtsfeld (bib0325) 2012 Oquab, Bottou, Laptev, Sivic (bib0110) 2014 Chen, Papandreou, Kokkinos, Murphy, Yuille (bib0365) 2016 Hazirbas, Ma, Domokos, Cremers (bib0570) 2016 Deng, Dong, Socher, Li, Li, Fei-Fei (bib0125) 2009 Ahmed, Yu, Xu, Gong, Xing (bib0105) 2008 Li, Yu (bib0545) 2016 Armeni, Sener, Zamir, Jiang, Brilakis, Fischer, Savarese (bib0335) 2016 Henaff, Bruna, LeCun (bib0605) 2015 Qi, Yi, Su, Guibas (bib0465) 2017 Sturgess, Alahari, Ladicky, Torr (bib0190) 2009 Hochreiter, Schmidhuber (bib0530) 1997; 9 Geiger, Lenz, Stiller, Urtasun (bib0295) 2013; 32 Zeng, Yu, Song, Suo, Walker, Rodriguez, Xiao (bib0560) 2017 Kipf, Welling (bib0610) 2016 Shelhamer, Rakelly, Hoffman, Darrell (bib0475) 2016 Rother, Kolmogorov, Blake (bib0505) 2004; vol. 23 Badrinarayanan, Kendall, Cipolla (bib0350) 2015; 39 Silberman, Hoiem, Kohli, Fergus (bib0245) 2012 Yu, Koltun (bib0375) 2015 Oberweger, Wohlhart, Lepetit (bib0020) 2015 Koltun (bib0515) 2011; 2 Graves, Fernández, Schmidhuber (bib0095) 2007 Simonyan (10.1016/j.asoc.2018.05.018_bib0075) 2014 Song (10.1016/j.asoc.2018.05.018_bib0255) 2015 Chang (10.1016/j.asoc.2018.05.018_bib0330) 2015 Lin (10.1016/j.asoc.2018.05.018_bib0600) 2017 Li (10.1016/j.asoc.2018.05.018_bib0545) 2016 Wang (10.1016/j.asoc.2018.05.018_bib0470) 2018 Henaff (10.1016/j.asoc.2018.05.018_bib0605) 2015 Alvarez (10.1016/j.asoc.2018.05.018_bib0195) 2012 Geiger (10.1016/j.asoc.2018.05.018_bib0295) 2013; 32 Janoch (10.1016/j.asoc.2018.05.018_bib0320) 2013 Pinheiro (10.1016/j.asoc.2018.05.018_bib0445) 2016 Perazzi (10.1016/j.asoc.2018.05.018_bib0235) 2016 Russakovsky (10.1016/j.asoc.2018.05.018_bib0130) 2015; 115 Roy (10.1016/j.asoc.2018.05.018_bib0395) 2016 Zhang (10.1016/j.asoc.2018.05.018_bib0575) 2014 Wong (10.1016/j.asoc.2018.05.018_bib0140) 2016 Liang-Chieh (10.1016/j.asoc.2018.05.018_bib0360) 2015 Anwar (10.1016/j.asoc.2018.05.018_bib0620) 2017; 13 Ess (10.1016/j.asoc.2018.05.018_bib0005) 2009 Noh (10.1016/j.asoc.2018.05.018_bib0080) 2015 Ning (10.1016/j.asoc.2018.05.018_bib0035) 2005; 14 Yosinski (10.1016/j.asoc.2018.05.018_bib0115) 2014 Brostow (10.1016/j.asoc.2018.05.018_bib0290) 2008 Zhang (10.1016/j.asoc.2018.05.018_bib0210) 2015 Paszke (10.1016/j.asoc.2018.05.018_bib0380) 2016 Richter (10.1016/j.asoc.2018.05.018_bib0135) 2016 Zhu (10.1016/j.asoc.2018.05.018_bib0060) 2016; 34 Kipf (10.1016/j.asoc.2018.05.018_bib0610) 2016 Krähenbühl (10.1016/j.asoc.2018.05.018_bib0520) 2013 Cordts (10.1016/j.asoc.2018.05.018_bib0180) 2015 Shelhamer (10.1016/j.asoc.2018.05.018_bib0475) 2016 Cho (10.1016/j.asoc.2018.05.018_bib0535) 2014 Szegedy (10.1016/j.asoc.2018.05.018_bib0085) 2015 Byeon (10.1016/j.asoc.2018.05.018_bib0425) 2015 Oberweger (10.1016/j.asoc.2018.05.018_bib0020) 2015 Ciresan (10.1016/j.asoc.2018.05.018_bib0040) 2012 Rother (10.1016/j.asoc.2018.05.018_bib0505) 2004; vol. 23 Farabet (10.1016/j.asoc.2018.05.018_bib0045) 2013; 35 Ros (10.1016/j.asoc.2018.05.018_bib0205) 2015 Yu (10.1016/j.asoc.2018.05.018_bib0375) 2015 Geiger (10.1016/j.asoc.2018.05.018_bib0010) 2012 Liu (10.1016/j.asoc.2018.05.018_bib0405) 2015 He (10.1016/j.asoc.2018.05.018_bib0090) 2016 Chen (10.1016/j.asoc.2018.05.018_bib0160) 2014 Pinheiro (10.1016/j.asoc.2018.05.018_bib0430) 2014 Pinheiro (10.1016/j.asoc.2018.05.018_bib0440) 2015 Han (10.1016/j.asoc.2018.05.018_bib0625) 2015 Pathak (10.1016/j.asoc.2018.05.018_bib0120) 2016 Badrinarayanan (10.1016/j.asoc.2018.05.018_bib0350) 2015; 39 Raj (10.1016/j.asoc.2018.05.018_bib0385) 2015 Tran (10.1016/j.asoc.2018.05.018_bib0480) 2016 Tran (10.1016/j.asoc.2018.05.018_bib0585) 2015 Richtsfeld (10.1016/j.asoc.2018.05.018_bib0325) 2012 Sturgess (10.1016/j.asoc.2018.05.018_bib0190) 2009 Girshick (10.1016/j.asoc.2018.05.018_bib0555) 2014 Zhou (10.1016/j.asoc.2018.05.018_bib0525) 2015 Deng (10.1016/j.asoc.2018.05.018_bib0125) 2009 Zhao (10.1016/j.asoc.2018.05.018_bib0410) 2016 Brostow (10.1016/j.asoc.2018.05.018_bib0185) 2009; 30 Zagoruyko (10.1016/j.asoc.2018.05.018_bib0450) 2016 Jain (10.1016/j.asoc.2018.05.018_bib0225) 2014 Koltun (10.1016/j.asoc.2018.05.018_bib0515) 2011; 2 Molchanov (10.1016/j.asoc.2018.05.018_bib0630) 2016 Ros (10.1016/j.asoc.2018.05.018_bib0200) 2015 Neverova (10.1016/j.asoc.2018.05.018_bib0485) 2017 Milletari (10.1016/j.asoc.2018.05.018_bib0595) 2016 Visin (10.1016/j.asoc.2018.05.018_bib0100) 2015 Hackel (10.1016/j.asoc.2018.05.018_bib0285) 2016 Hazirbas (10.1016/j.asoc.2018.05.018_bib0570) 2016 Ros (10.1016/j.asoc.2018.05.018_bib0175) 2016 Everingham (10.1016/j.asoc.2018.05.018_bib0150) 2015; 111 Yi (10.1016/j.asoc.2018.05.018_bib0265) 2016 Liu (10.1016/j.asoc.2018.05.018_bib0220) 2009 Bell (10.1016/j.asoc.2018.05.018_bib0230) 2015 Chen (10.1016/j.asoc.2018.05.018_bib0365) 2016 Thoma (10.1016/j.asoc.2018.05.018_bib0065) 2016 Hochreiter (10.1016/j.asoc.2018.05.018_bib0530) 1997; 9 Yoon (10.1016/j.asoc.2018.05.018_bib0025) 2015 Ma (10.1016/j.asoc.2018.05.018_bib0565) 2017 Hariharan (10.1016/j.asoc.2018.05.018_bib0165) 2011 Qi (10.1016/j.asoc.2018.05.018_bib0465) 2017 Li (10.1016/j.asoc.2018.05.018_bib0420) 2016 Krizhevsky (10.1016/j.asoc.2018.05.018_bib0070) 2012 Shuai (10.1016/j.asoc.2018.05.018_bib0435) 2016 Roy (10.1016/j.asoc.2018.05.018_bib0590) 2017; 8 Bell (10.1016/j.asoc.2018.05.018_bib0305) 2013; 32 Visin (10.1016/j.asoc.2018.05.018_bib0415) 2016 Bian (10.1016/j.asoc.2018.05.018_bib0400) 2016 Wan (10.1016/j.asoc.2018.05.018_bib0030) 2014 Russell (10.1016/j.asoc.2018.05.018_bib0310) 2008; 77 Zeiler (10.1016/j.asoc.2018.05.018_bib0495) 2014 Gould (10.1016/j.asoc.2018.05.018_bib0215) 2009 Lin (10.1016/j.asoc.2018.05.018_bib0170) 2014 Zeng (10.1016/j.asoc.2018.05.018_bib0560) 2017 Arbeláez (10.1016/j.asoc.2018.05.018_bib0550) 2014 Gupta (10.1016/j.asoc.2018.05.018_bib0315) 2013 Graves (10.1016/j.asoc.2018.05.018_bib0095) 2007 Li (10.1016/j.asoc.2018.05.018_bib0540) 2016 Qi (10.1016/j.asoc.2018.05.018_bib0460) 2016 Chen (10.1016/j.asoc.2018.05.018_bib0275) 2009; 28 Quadros (10.1016/j.asoc.2018.05.018_bib0280) 2012 Zhang (10.1016/j.asoc.2018.05.018_bib0500) 2017 Kendall (10.1016/j.asoc.2018.05.018_bib0355) 2015 Huang (10.1016/j.asoc.2018.05.018_bib0455) 2016 Zheng (10.1016/j.asoc.2018.05.018_bib0370) 2015 Long (10.1016/j.asoc.2018.05.018_bib0340) 2015 Hariharan (10.1016/j.asoc.2018.05.018_bib0050) 2014 Ahmed (10.1016/j.asoc.2018.05.018_bib0105) 2008 Boykov (10.1016/j.asoc.2018.05.018_bib0580) 2001; 23 Pont-Tuset (10.1016/j.asoc.2018.05.018_bib0240) 2017 Xiao (10.1016/j.asoc.2018.05.018_bib0250) 2013 Prest (10.1016/j.asoc.2018.05.018_bib0300) 2012 Eigen (10.1016/j.asoc.2018.05.018_bib0390) 2015 Shotton (10.1016/j.asoc.2018.05.018_bib0510) 2009; 81 Cordts (10.1016/j.asoc.2018.05.018_bib0015) 2016 Silberman (10.1016/j.asoc.2018.05.018_bib0245) 2012 Armeni (10.1016/j.asoc.2018.05.018_bib0270) 2017 Niepert (10.1016/j.asoc.2018.05.018_bib0615) 2016 Mottaghi (10.1016/j.asoc.2018.05.018_bib0155) 2014 Oquab (10.1016/j.asoc.2018.05.018_bib0110) 2014 Ronneberger (10.1016/j.asoc.2018.05.018_bib0345) 2015 Lai (10.1016/j.asoc.2018.05.018_bib0260) 2011 Armeni (10.1016/j.asoc.2018.05.018_bib0335) 2016 Gupta (10.1016/j.asoc.2018.05.018_bib0055) 2014 Zeiler (10.1016/j.asoc.2018.05.018_bib0490) 2011 Shen (10.1016/j.asoc.2018.05.018_bib0145) 2016; vol. 35 |
| References_xml | – year: 2009 ident: bib0190 article-title: Combining appearance and structure from motion features for road scene understanding publication-title: BMVC 2012 – 23rd British Machine Vision Conference, BMVA – start-page: 1 year: 2016 end-page: 6 ident: bib0140 article-title: Understanding data augmentation for classification: when to warp? publication-title: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA) – start-page: 513 year: 2013 end-page: 521 ident: bib0520 article-title: Parameter learning and convergent inference for dense random fields publication-title: ICML (3) – start-page: 1625 year: 2013 end-page: 1632 ident: bib0250 article-title: SUN3D: a database of big spaces reconstructed using SfM and object labels publication-title: 2013 IEEE International Conference on Computer Vision – volume: 28 year: 2009 ident: bib0275 article-title: A benchmark for 3D mesh segmentation publication-title: ACM Trans. Graph. (Proc. SIGGRAPH) – start-page: 852 year: 2016 end-page: 868 ident: bib0475 article-title: Clockwork convnets for video semantic segmentation publication-title: Computer Vision – ECCV 2016 Workshops – start-page: 1520 year: 2015 end-page: 1528 ident: bib0080 article-title: Learning deconvolution network for semantic segmentation publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 2 year: 2009 ident: bib0005 article-title: Segmentation-based urban traffic scene understanding publication-title: BMVC, vol. 1 – year: 2015 ident: bib0100 article-title: Renet: A Recurrent Neural Network Based Alternative to Convolutional Networks, CoRR abs/1505.00393 – start-page: 3282 year: 2012 end-page: 3289 ident: bib0300 article-title: Learning object class detectors from weakly annotated video publication-title: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – year: 2014 ident: bib0155 article-title: The role of context for object detection and semantic segmentation in the wild publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – year: 2017 ident: bib0485 article-title: Predicting Deeper into the Future of Semantic Segmentation, CoRR abs/1703.07684 – start-page: 1529 year: 2015 end-page: 1537 ident: bib0370 article-title: Conditional random fields as recurrent neural networks publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 345 year: 2014 end-page: 360 ident: bib0055 article-title: Learning rich features from RGB-D images for object detection and segmentation publication-title: European Conference on Computer Vision – year: 2015 ident: bib0375 article-title: Multi-scale Context Aggregation by Dilated Convolutions – start-page: 17 year: 2016 end-page: 24 ident: bib0480 article-title: Deep end2end voxel2voxel prediction publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops – year: 2015 ident: bib0605 article-title: Deep Convolutional Networks on Graph-Structured Data – start-page: 564 year: 2013 end-page: 571 ident: bib0315 article-title: Perceptual organization and recognition of indoor scenes from RGB-D images publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2015 ident: bib0330 article-title: Shapenet: An Information-Rich 3D Model Repository – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: bib0530 article-title: Long short-term memory publication-title: Neural Comput. – start-page: 770 year: 2016 end-page: 778 ident: bib0090 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2017 ident: bib0270 article-title: Joint 2D-3D-Semantic Data for Indoor Scene Understanding – year: 2016 ident: bib0595 article-title: V-net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation, CoRR abs/1606.04797 – year: 2015 ident: bib0020 article-title: Hands Deep in Deep Learning for Hand Pose Estimation – volume: 77 start-page: 157 year: 2008 end-page: 173 ident: bib0310 article-title: Labelme: a database and web-based tool for image annotation publication-title: Int. J. Comput. Vis. – start-page: 3354 year: 2012 end-page: 3361 ident: bib0010 article-title: Are we ready for autonomous driving? The KITTI vision benchmark suite publication-title: 2012 IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: bib0415 article-title: ReSeg: a recurrent neural network-based model for semantic segmentation publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – volume: vol. 23 start-page: 309 year: 2004 end-page: 314 ident: bib0505 article-title: GrabCut: interactive foreground extraction using iterated graph cuts publication-title: ACM Transactions on Graphics (TOG) – volume: vol. 35 start-page: 93 year: 2016 end-page: 102 ident: bib0145 article-title: Automatic portrait segmentation for image stylization publication-title: Computer Graphics Forum – volume: 32 year: 2013 ident: bib0305 article-title: OpenSurfaces: a richly annotated catalog of surface appearance publication-title: ACM Trans. Graph. (SIGGRAPH) – start-page: 24 year: 2015 end-page: 32 ident: bib0025 article-title: Learning a deep convolutional network for light-field image super-resolution publication-title: Proceedings of the IEEE International Conference on Computer Vision Workshops – start-page: 186 year: 2016 end-page: 201 ident: bib0395 article-title: A multi-scale CNN for affordance segmentation in RGB images publication-title: European Conference on Computer Vision – start-page: 75 year: 2016 end-page: 91 ident: bib0445 article-title: Learning to refine object segments publication-title: European Conference on Computer Vision – year: 2016 ident: bib0450 article-title: A multipath network for object detection publication-title: Proceedings of the British Machine Vision Conference 2016, BMVC 2016 – start-page: 82 year: 2014 end-page: 90 ident: bib0430 article-title: Recurrent convolutional neural networks for scene labeling publication-title: ICML – start-page: 2843 year: 2012 end-page: 2851 ident: bib0040 article-title: Deep neural networks segment neuronal membranes in electron microscopy images publication-title: Advances in Neural Information Processing Systems – volume: 35 start-page: 1915 year: 2013 end-page: 1929 ident: bib0045 article-title: Learning hierarchical features for scene labeling publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 580 year: 2014 end-page: 587 ident: bib0555 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 111 start-page: 98 year: 2015 end-page: 136 ident: bib0150 article-title: The PASCAL visual object classes challenge: a retrospective publication-title: Int. J. Comput. Vis. – start-page: 991 year: 2011 end-page: 998 ident: bib0165 article-title: Semantic contours from inverse detectors publication-title: 2011 International Conference on Computer Vision – start-page: 3431 year: 2015 end-page: 3440 ident: bib0340 article-title: Fully convolutional networks for semantic segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2015 ident: bib0180 article-title: The cityscapes dataset publication-title: CVPR Workshop on The Future of Datasets in Vision – start-page: 2650 year: 2015 end-page: 2658 ident: bib0390 article-title: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture publication-title: Proceedings of the IEEE International Conference on Computer Vision – year: 2016 ident: bib0540 article-title: RGB-D Scene Labeling with Long Short-Term Memorized Fusion Model, CoRR abs/1604.05000 – start-page: 537 year: 2015 end-page: 542 ident: bib0200 article-title: Unsupervised image transformation for outdoor semantic labelling publication-title: 2015 IEEE Intelligent Vehicles Symposium (IV) – volume: 23 start-page: 1222 year: 2001 end-page: 1239 ident: bib0580 article-title: Fast approximate energy minimization via graph cuts publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2018 ident: bib0470 article-title: Dynamic Graph CNN for Learning on Point Clouds – year: 2017 ident: bib0565 article-title: Multi-view Deep Learning for Consistent Semantic Mapping with RGB-D Cameras – volume: 2 start-page: 4 year: 2011 ident: bib0515 article-title: Efficient inference in fully connected CRFs with Gaussian edge potentials publication-title: Adv. Neural Inf. Process. Syst. – year: 2016 ident: bib0460 article-title: PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation – start-page: 141 year: 2013 end-page: 165 ident: bib0320 article-title: A Category-Level 3D Object Dataset: Putting the Kinect to Work – start-page: 3234 year: 2016 end-page: 3243 ident: bib0175 article-title: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 81 start-page: 2 year: 2009 end-page: 23 ident: bib0510 article-title: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context publication-title: Int. J. Comput. Vis. – year: 2017 ident: bib0600 article-title: Focal loss for dense object detection publication-title: International Conference on Computer Vision (ICCV) – volume: 14 start-page: 1360 year: 2005 end-page: 1371 ident: bib0035 article-title: Toward automatic phenotyping of developing embryos from videos publication-title: IEEE Trans. Image Process. – start-page: 549 year: 2007 end-page: 558 ident: bib0095 article-title: Multi-dimensional Recurrent Neural Networks – start-page: 541 year: 2016 end-page: 557 ident: bib0420 article-title: LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling – start-page: 478 year: 2016 end-page: 487 ident: bib0545 article-title: Deep contrast learning for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: bib0235 article-title: A benchmark dataset and evaluation methodology for video object segmentation publication-title: Computer Vision and Pattern Recognition – start-page: 157 year: 2014 end-page: 166 ident: bib0030 article-title: Deep learning for content-based image retrieval: a comprehensive study publication-title: Proceedings of the 22nd ACM International Conference on Multimedia – volume: 13 start-page: 32 year: 2017 ident: bib0620 article-title: Structured pruning of deep convolutional neural networks publication-title: ACM J. Emerg. Technol. Comput. Syst. – year: 2015 ident: bib0405 article-title: Parsenet: Looking Wider to See Better – start-page: 1534 year: 2016 end-page: 1543 ident: bib0335 article-title: 3D semantic parsing of large-scale indoor spaces publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 8 start-page: 3627 year: 2017 end-page: 3642 ident: bib0590 article-title: ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks publication-title: Biomed. Opt. Express – volume: 115 start-page: 211 year: 2015 end-page: 252 ident: bib0130 article-title: Imagenet large scale visual recognition challenge publication-title: Int. J. Comput. Vis. – year: 2015 ident: bib0625 article-title: Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding – start-page: 248 year: 2009 end-page: 255 ident: bib0125 article-title: ImageNet: a large-scale hierarchical image database publication-title: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009 – year: 2015 ident: bib0355 article-title: Bayesian Segnet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding – year: 2016 ident: bib0570 article-title: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture publication-title: Proc. ACCV, vol. 2 – start-page: 1850 year: 2015 end-page: 1857 ident: bib0210 article-title: Sensor fusion for semantic segmentation of urban scenes publication-title: 2015 IEEE International Conference on Robotics and Automation (ICRA) – year: 2015 ident: bib0525 article-title: Exploiting Local Structures with the Kronecker Layer in Convolutional Networks – start-page: 69 year: 2008 end-page: 82 ident: bib0105 article-title: Training hierarchical feed-forward visual recognition models using transfer learning from pseudo-tasks publication-title: European Conference on Computer Vision – start-page: 567 year: 2015 end-page: 576 ident: bib0255 article-title: SUN RGB-D: a RGB-D scene understanding benchmark suite publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2012 ident: bib0325 article-title: The Object Segmentation Database (OSD) – year: 2016 ident: bib0380 article-title: Enet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation – start-page: 102 year: 2016 end-page: 118 ident: bib0135 article-title: Playing for Data: Ground Truth from Computer Games – start-page: 103 year: 2014 end-page: 111 ident: bib0535 article-title: On the properties of neural machine translation: encoder-decoder approaches publication-title: Proceedings of SSST@EMNLP 2014, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation – volume: 34 start-page: 12 year: 2016 end-page: 27 ident: bib0060 article-title: Beyond pixels: a comprehensive survey from bottom-up to semantic image segmentation and cosegmentation publication-title: J. Vis. Commun. Image Represent. – start-page: 3320 year: 2014 end-page: 3328 ident: bib0115 article-title: How transferable are features in deep neural networks? publication-title: Advances in Neural Information Processing Systems – start-page: 1717 year: 2014 end-page: 1724 ident: bib0110 article-title: Learning and transferring mid-level image representations using convolutional neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 32 start-page: 1231 year: 2013 end-page: 1237 ident: bib0295 article-title: Vision meets robotics: the KITTI dataset publication-title: Int. J. Robot. Res. – start-page: 1 year: 2009 end-page: 8 ident: bib0215 article-title: Decomposing a scene into geometric and semantically consistent regions publication-title: 2009 IEEE 12th International Conference on Computer Vision – start-page: 746 year: 2012 end-page: 760 ident: bib0245 article-title: Indoor segmentation and support inference from RGBD images publication-title: European Conference on Computer Vision – volume: 39 start-page: 2481 year: 2015 end-page: 2495 ident: bib0350 article-title: Segnet: a deep convolutional encoder-decoder architecture for scene segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1097 year: 2012 end-page: 1105 ident: bib0070 article-title: ImageNet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – start-page: 44 year: 2008 end-page: 57 ident: bib0290 article-title: Segmentation and recognition using structure from motion point clouds publication-title: European Conference on Computer Vision – start-page: 328 year: 2014 end-page: 335 ident: bib0550 article-title: Multiscale combinatorial grouping publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 5105 year: 2017 end-page: 5114 ident: bib0465 article-title: PointNet++: deep hierarchical feature learning on point sets in a metric space publication-title: Advances in Neural Information Processing Systems – year: 2016 ident: bib0120 article-title: Context Encoders: Feature Learning by Inpainting, CoRR abs/1604.07379 – start-page: 1817 year: 2011 end-page: 1824 ident: bib0260 article-title: A large-scale hierarchical multi-view RGB-D object dataset publication-title: 2011 IEEE International Conference on Robotics and Automation (ICRA) – year: 2016 ident: bib0630 article-title: Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning – start-page: 3213 year: 2016 end-page: 3223 ident: bib0015 article-title: The cityscapes dataset for semantic urban scene understanding publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2017 ident: bib0240 article-title: The 2017 Davis Challenge on Video Object Segmentation – start-page: 3547 year: 2015 end-page: 3555 ident: bib0425 article-title: Scene labeling with LSTM recurrent neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2017 ident: bib0500 article-title: Road Extraction by Deep Residual U-Net, CoRR abs/1711.10684 – start-page: 321 year: 2014 end-page: 326 ident: bib0575 article-title: Discriminative feature learning for video semantic segmentation publication-title: 2014 International Conference on Virtual Reality and Visualization (ICVRV) – year: 2016 ident: bib0615 article-title: Learning convolutional neural networks for graphs publication-title: Proceedings of the 33rd Annual International Conference on Machine Learning – year: 2016 ident: bib0610 article-title: Semi-supervised Classification with Graph Convolutional Networks – year: 2016 ident: bib0455 article-title: Point cloud labeling using 3D convolutional neural network publication-title: Proc. of the International Conf. on Pattern Recognition (ICPR), vol. 2 – year: 2016 ident: bib0410 article-title: Pyramid Scene Parsing Network, CoRR abs/1612.01105 – start-page: 1 year: 2016 end-page: 8 ident: bib0400 article-title: Multiscale fully convolutional network with application to industrial inspection publication-title: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) – start-page: 1972 year: 2009 end-page: 1979 ident: bib0220 article-title: Nonparametric scene parsing: label transfer via dense scene alignment publication-title: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009 – start-page: 818 year: 2014 end-page: 833 ident: bib0495 article-title: Visualizing and understanding convolutional networks publication-title: European Conference on Computer Vision – start-page: 1383 year: 2017 end-page: 1386 ident: bib0560 article-title: Multi-view self-supervised deep learning for 6D pose estimation in the Amazon picking challenge publication-title: 2017 IEEE International Conference on Robotics and Automation (ICRA) – year: 2016 ident: bib0265 article-title: A scalable active framework for region annotation in 3D shape collections publication-title: SIGGRAPH Asia – start-page: 2018 year: 2011 end-page: 2025 ident: bib0490 article-title: Adaptive deconvolutional networks for mid and high level feature learning publication-title: 2011 IEEE International Conference on Computer Vision (ICCV) – start-page: 376 year: 2012 end-page: 389 ident: bib0195 article-title: Road scene segmentation from a single image publication-title: European Conference on Computer Vision – year: 2016 ident: bib0365 article-title: Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs, CoRR abs/1606.00915 – start-page: 231 year: 2015 end-page: 238 ident: bib0205 article-title: Vision-based offline-online perception paradigm for autonomous driving publication-title: 2015 IEEE Winter Conference on Applications of Computer Vision (WACV) – start-page: 1 year: 2015 end-page: 9 ident: bib0085 article-title: Going deeper with convolutions publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2014 ident: bib0160 article-title: Detect what you can: detecting and representing objects using holistic models and body parts publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 1990 year: 2015 end-page: 1998 ident: bib0440 article-title: Learning to segment object candidates publication-title: Advances in Neural Information Processing Systems – start-page: 4489 year: 2015 end-page: 4497 ident: bib0585 article-title: Learning spatiotemporal features with 3D convolutional networks publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 234 year: 2015 end-page: 241 ident: bib0345 article-title: U-Net: convolutional networks for biomedical image segmentation publication-title: Medical Image Computing and Computer-Assisted Intervention (MICCAI), vol. 9351 of LNCS – volume: 30 start-page: 88 year: 2009 end-page: 97 ident: bib0185 article-title: Semantic object classes in video: a high-definition ground truth database publication-title: Pattern Recognit. Lett. – start-page: 1610 year: 2016 end-page: 1618 ident: bib0285 article-title: Contour detection in unstructured 3D point clouds publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2012 ident: bib0280 article-title: An occlusion-aware feature for range images publication-title: IEEE International Conference on Robotics and Automation, 2012, ICRA’12 – start-page: 297 year: 2014 end-page: 312 ident: bib0050 article-title: Simultaneous detection and segmentation publication-title: European Conference on Computer Vision – start-page: 740 year: 2014 end-page: 755 ident: bib0170 article-title: Microsoft coco: common objects in context publication-title: European Conference on Computer Vision – start-page: 656 year: 2014 end-page: 671 ident: bib0225 article-title: Supervoxel-consistent foreground propagation in video publication-title: European Conference on Computer Vision – year: 2015 ident: bib0360 article-title: Semantic image segmentation with deep convolutional nets and fully connected CRFs publication-title: International Conference on Learning Representations – start-page: 3479 year: 2015 end-page: 3487 ident: bib0230 article-title: Material recognition in the wild with the materials in context database publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: bib0065 article-title: A Survey of Semantic Segmentation, CoRR abs/1602.06541 – year: 2014 ident: bib0075 article-title: Very Deep Convolutional Networks for Large-Scale Image Recognition – start-page: 3620 year: 2016 end-page: 3629 ident: bib0435 article-title: DAG-recurrent neural networks for scene labeling publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2015 ident: bib0385 article-title: Multi-scale Convolutional Architecture for Semantic Segmentation – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0405 – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0625 – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0605 – start-page: 157 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0030 article-title: Deep learning for content-based image retrieval: a comprehensive study – year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0485 – year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0160 article-title: Detect what you can: detecting and representing objects using holistic models and body parts publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 75 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0445 article-title: Learning to refine object segments – start-page: 1717 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0110 article-title: Learning and transferring mid-level image representations using convolutional neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0595 – volume: 13 start-page: 32 issue: 3 year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0620 article-title: Structured pruning of deep convolutional neural networks publication-title: ACM J. Emerg. Technol. Comput. Syst. doi: 10.1145/3005348 – start-page: 746 year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0245 article-title: Indoor segmentation and support inference from RGBD images – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0460 – start-page: 328 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0550 article-title: Multiscale combinatorial grouping publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0570 article-title: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture publication-title: Proc. ACCV, vol. 2 – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0020 – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.asoc.2018.05.018_bib0530 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – start-page: 44 year: 2008 ident: 10.1016/j.asoc.2018.05.018_bib0290 article-title: Segmentation and recognition using structure from motion point clouds – start-page: 3354 year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0010 article-title: Are we ready for autonomous driving? The KITTI vision benchmark suite publication-title: 2012 IEEE Conference on Computer Vision and Pattern Recognition doi: 10.1109/CVPR.2012.6248074 – year: 2018 ident: 10.1016/j.asoc.2018.05.018_bib0470 – start-page: 24 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0025 article-title: Learning a deep convolutional network for light-field image super-resolution publication-title: Proceedings of the IEEE International Conference on Computer Vision Workshops – year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0240 – volume: 77 start-page: 157 issue: 1 year: 2008 ident: 10.1016/j.asoc.2018.05.018_bib0310 article-title: Labelme: a database and web-based tool for image annotation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-007-0090-8 – start-page: 2018 year: 2011 ident: 10.1016/j.asoc.2018.05.018_bib0490 article-title: Adaptive deconvolutional networks for mid and high level feature learning – start-page: 580 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0555 article-title: Rich feature hierarchies for accurate object detection and semantic segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 991 year: 2011 ident: 10.1016/j.asoc.2018.05.018_bib0165 article-title: Semantic contours from inverse detectors – start-page: 1 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0400 article-title: Multiscale fully convolutional network with application to industrial inspection – start-page: 4489 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0585 article-title: Learning spatiotemporal features with 3D convolutional networks publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 231 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0205 article-title: Vision-based offline-online perception paradigm for autonomous driving – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0065 – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0120 – volume: 32 issue: 4 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0305 article-title: OpenSurfaces: a richly annotated catalog of surface appearance publication-title: ACM Trans. Graph. (SIGGRAPH) doi: 10.1145/2461912.2462002 – start-page: 818 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0495 article-title: Visualizing and understanding convolutional networks – start-page: 1610 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0285 article-title: Contour detection in unstructured 3D point clouds publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 81 start-page: 2 issue: 1 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0510 article-title: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-007-0109-1 – start-page: 1383 year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0560 article-title: Multi-view self-supervised deep learning for 6D pose estimation in the Amazon picking challenge – volume: 115 start-page: 211 issue: 3 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0130 article-title: Imagenet large scale visual recognition challenge publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-015-0816-y – start-page: 141 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0320 – start-page: 248 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0125 article-title: ImageNet: a large-scale hierarchical image database – start-page: 549 year: 2007 ident: 10.1016/j.asoc.2018.05.018_bib0095 – volume: 32 start-page: 1231 issue: 11 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0295 article-title: Vision meets robotics: the KITTI dataset publication-title: Int. J. Robot. Res. doi: 10.1177/0278364913491297 – start-page: 82 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0430 article-title: Recurrent convolutional neural networks for scene labeling publication-title: ICML – start-page: 103 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0535 article-title: On the properties of neural machine translation: encoder-decoder approaches – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0365 – start-page: 3213 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0015 article-title: The cityscapes dataset for semantic urban scene understanding publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1625 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0250 article-title: SUN3D: a database of big spaces reconstructed using SfM and object labels publication-title: 2013 IEEE International Conference on Computer Vision doi: 10.1109/ICCV.2013.458 – start-page: 770 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0090 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0100 – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0380 – year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0500 – volume: vol. 35 start-page: 93 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0145 article-title: Automatic portrait segmentation for image stylization – volume: 2 start-page: 4 issue: 3 year: 2011 ident: 10.1016/j.asoc.2018.05.018_bib0515 article-title: Efficient inference in fully connected CRFs with Gaussian edge potentials publication-title: Adv. Neural Inf. Process. Syst. – start-page: 321 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0575 article-title: Discriminative feature learning for video semantic segmentation – start-page: 345 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0055 article-title: Learning rich features from RGB-D images for object detection and segmentation – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0375 – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0610 – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0415 article-title: ReSeg: a recurrent neural network-based model for semantic segmentation publication-title: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0630 – volume: 30 start-page: 88 issue: 2 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0185 article-title: Semantic object classes in video: a high-definition ground truth database publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2008.04.005 – start-page: 740 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0170 article-title: Microsoft coco: common objects in context – start-page: 5105 year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0465 article-title: PointNet++: deep hierarchical feature learning on point sets in a metric space – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0450 article-title: A multipath network for object detection – start-page: 2 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0005 article-title: Segmentation-based urban traffic scene understanding publication-title: BMVC, vol. 1 – start-page: 297 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0050 article-title: Simultaneous detection and segmentation – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0180 article-title: The cityscapes dataset publication-title: CVPR Workshop on The Future of Datasets in Vision – start-page: 3431 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0340 article-title: Fully convolutional networks for semantic segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 111 start-page: 98 issue: 1 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0150 article-title: The PASCAL visual object classes challenge: a retrospective publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-014-0733-5 – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0525 – start-page: 102 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0135 – start-page: 1850 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0210 article-title: Sensor fusion for semantic segmentation of urban scenes – start-page: 478 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0545 article-title: Deep contrast learning for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0280 article-title: An occlusion-aware feature for range images – year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0325 – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0330 – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0410 – start-page: 513 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0520 article-title: Parameter learning and convergent inference for dense random fields publication-title: ICML (3) – start-page: 1534 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0335 article-title: 3D semantic parsing of large-scale indoor spaces publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0540 – start-page: 2650 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0390 article-title: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 1972 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0220 article-title: Nonparametric scene parsing: label transfer via dense scene alignment – start-page: 3620 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0435 article-title: DAG-recurrent neural networks for scene labeling publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 186 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0395 article-title: A multi-scale CNN for affordance segmentation in RGB images – year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0155 article-title: The role of context for object detection and semantic segmentation in the wild publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – start-page: 1097 year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0070 article-title: ImageNet classification with deep convolutional neural networks – start-page: 1817 year: 2011 ident: 10.1016/j.asoc.2018.05.018_bib0260 article-title: A large-scale hierarchical multi-view RGB-D object dataset – start-page: 656 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0225 article-title: Supervoxel-consistent foreground propagation in video – start-page: 567 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0255 article-title: SUN RGB-D: a RGB-D scene understanding benchmark suite publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 8 start-page: 3627 issue: 8 year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0590 article-title: ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks publication-title: Biomed. Opt. Express doi: 10.1364/BOE.8.003627 – volume: 14 start-page: 1360 issue: 9 year: 2005 ident: 10.1016/j.asoc.2018.05.018_bib0035 article-title: Toward automatic phenotyping of developing embryos from videos publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2005.852470 – volume: vol. 23 start-page: 309 year: 2004 ident: 10.1016/j.asoc.2018.05.018_bib0505 article-title: GrabCut: interactive foreground extraction using iterated graph cuts – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0235 article-title: A benchmark dataset and evaluation methodology for video object segmentation publication-title: Computer Vision and Pattern Recognition – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0355 – start-page: 3547 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0425 article-title: Scene labeling with LSTM recurrent neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0265 article-title: A scalable active framework for region annotation in 3D shape collections publication-title: SIGGRAPH Asia doi: 10.1145/2980179.2980238 – volume: 28 issue: 3 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0275 article-title: A benchmark for 3D mesh segmentation publication-title: ACM Trans. Graph. (Proc. SIGGRAPH) doi: 10.1145/1531326.1531379 – start-page: 376 year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0195 article-title: Road scene segmentation from a single image – start-page: 69 year: 2008 ident: 10.1016/j.asoc.2018.05.018_bib0105 article-title: Training hierarchical feed-forward visual recognition models using transfer learning from pseudo-tasks – start-page: 1990 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0440 article-title: Learning to segment object candidates – start-page: 3234 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0175 article-title: The synthia dataset: a large collection of synthetic images for semantic segmentation of urban scenes publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2843 year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0040 article-title: Deep neural networks segment neuronal membranes in electron microscopy images – volume: 34 start-page: 12 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0060 article-title: Beyond pixels: a comprehensive survey from bottom-up to semantic image segmentation and cosegmentation publication-title: J. Vis. Commun. Image Represent. doi: 10.1016/j.jvcir.2015.10.012 – start-page: 234 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0345 article-title: U-Net: convolutional networks for biomedical image segmentation – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0360 article-title: Semantic image segmentation with deep convolutional nets and fully connected CRFs publication-title: International Conference on Learning Representations – volume: 23 start-page: 1222 issue: 11 year: 2001 ident: 10.1016/j.asoc.2018.05.018_bib0580 article-title: Fast approximate energy minimization via graph cuts publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.969114 – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0615 article-title: Learning convolutional neural networks for graphs – year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0455 article-title: Point cloud labeling using 3D convolutional neural network publication-title: Proc. of the International Conf. on Pattern Recognition (ICPR), vol. 2 – start-page: 3320 year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0115 article-title: How transferable are features in deep neural networks? – start-page: 537 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0200 article-title: Unsupervised image transformation for outdoor semantic labelling – start-page: 852 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0475 article-title: Clockwork convnets for video semantic segmentation – volume: 35 start-page: 1915 issue: 8 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0045 article-title: Learning hierarchical features for scene labeling publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.231 – year: 2014 ident: 10.1016/j.asoc.2018.05.018_bib0075 – start-page: 3282 year: 2012 ident: 10.1016/j.asoc.2018.05.018_bib0300 article-title: Learning object class detectors from weakly annotated video – start-page: 1 year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0215 article-title: Decomposing a scene into geometric and semantically consistent regions – start-page: 1 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0140 article-title: Understanding data augmentation for classification: when to warp? – volume: 39 start-page: 2481 issue: 12 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0350 article-title: Segnet: a deep convolutional encoder-decoder architecture for scene segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2644615 – start-page: 17 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0480 article-title: Deep end2end voxel2voxel prediction publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops – year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0600 article-title: Focal loss for dense object detection – year: 2009 ident: 10.1016/j.asoc.2018.05.018_bib0190 article-title: Combining appearance and structure from motion features for road scene understanding publication-title: BMVC 2012 – 23rd British Machine Vision Conference, BMVA – start-page: 541 year: 2016 ident: 10.1016/j.asoc.2018.05.018_bib0420 – start-page: 1520 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0080 article-title: Learning deconvolution network for semantic segmentation publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 1 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0085 article-title: Going deeper with convolutions publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0385 – start-page: 564 year: 2013 ident: 10.1016/j.asoc.2018.05.018_bib0315 article-title: Perceptual organization and recognition of indoor scenes from RGB-D images publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0565 – start-page: 3479 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0230 article-title: Material recognition in the wild with the materials in context database publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2017 ident: 10.1016/j.asoc.2018.05.018_bib0270 – start-page: 1529 year: 2015 ident: 10.1016/j.asoc.2018.05.018_bib0370 article-title: Conditional random fields as recurrent neural networks publication-title: Proceedings of the IEEE International Conference on Computer Vision |
| SSID | ssj0016928 |
| Score | 2.6765494 |
| SecondaryResourceType | review_article |
| Snippet | •An in-depth review of deep learning methods for semantic segmentation applied to various areas.•An overview of background concepts and formulation for... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 41 |
| SubjectTerms | Deep learning Scene labeling Semantic segmentation |
| Title | A survey on deep learning techniques for image and video semantic segmentation |
| URI | https://dx.doi.org/10.1016/j.asoc.2018.05.018 |
| Volume | 70 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07a8MwEBYhXbr0XZo-goZuRY1tSbY0htCQvkJpU8hmJFkKKY0T8ih06W-vZMuhhZKhk2xzh8Xn850OvrsD4DLSIg4Zo4hynCHCY4mYEgyZSDMpJMdhUS722I97r-RuSIc10KlqYRyt0vv-0qcX3to_aXk0W7PxuPViMw9GOLGvwjZIFpNrCUmclV9_rWkeYcyL-apOGDlpXzhTcryERcDRu1jZvZP9HZx-BJzuHtjxJ0XYLjezD2o6PwC71RQG6H_KQ9Bvw8Vq_qE_4TSHmdYz6CdBjOC6QesC2rMpHE-s84Aiz6ArvpvChZ5YXMfKXowmvgYpPwKD7s2g00N-SgJSOAiWyFCbQQlFTBwzE3GlbVQyPDOSSkk1NsKoUASZNkmcxJRmQrGAkTBSJsCah_gY1PNprk8AzHAmbQZhNV2aoghPJKeJNvZTBlQy3ABhhU6qfAdxN8jiPa2oYm-pQzR1iKYBTe3SAFdrnVnZP2OjNK1AT39ZQWod_Aa903_qnYFtd1dyxs5BfTlf6Qt7yFjKZmFFTbDV7jw_PLn19r7X_waYcNMs |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NT9swFH8CdoALMD40YGw-jBMKTeI4tQ87oG1VGbQXitSbZTt2VbSmFS0gLvxR_IV7bpwKpKmHSZwSJXmJ8_PT-5Deez-Ab6lVecI5i5igRZSJXEfcKB651HKttKDJvF2s083bN9nvPuuvwEvdC-PLKoPtr2z63FqHK42AZmMyHDauMfPgmcjwUxSdZFIzWF_ap0fM26bfL37iJp-kaetX70c7CtQCkaFxPIscw7RDmczlOXepMBZNuROF00xrZqlTziQqLqxr5s2csUIZHvMsSY2LqRUJxdeuwocMrYVnTTh7XpSVJLmY87n6xUV-daFRp6opU4i4Lyfj1bRQ_m9n-MrBtbZhM0Sm5Lz6-Y-wYssd2KpZH0gwArvQPSfT-7sH-0TGJSmsnZDAPDEgi4GwU4KxMBmO0FgRVRbEN_uNydSOcB-HBk8Go9DzVO5B7z2g24e1clzaT0AKWmjMWFDSp0UmE00tWNM6VJ2YaU4PIKnRkSZMLPfEGX9kXZp2Kz2i0iMqYybxcACnC5lJNa9j6dOsBl2-0TqJDmWJ3OF_yn2F9XavcyWvLrqXR7Dh71T1ap9hbXZ3b48xwJnpL3ONIiDfWYP_AodjDiA |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+survey+on+deep+learning+techniques+for+image+and+video+semantic+segmentation&rft.jtitle=Applied+soft+computing&rft.au=Garcia-Garcia%2C+Alberto&rft.au=Orts-Escolano%2C+Sergio&rft.au=Oprea%2C+Sergiu&rft.au=Villena-Martinez%2C+Victor&rft.date=2018-09-01&rft.pub=Elsevier+B.V&rft.issn=1568-4946&rft.eissn=1872-9681&rft.volume=70&rft.spage=41&rft.epage=65&rft_id=info:doi/10.1016%2Fj.asoc.2018.05.018&rft.externalDocID=S1568494618302813 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1568-4946&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1568-4946&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1568-4946&client=summon |