T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos
The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks, such as GoogleNet and VGG, novel object detection frameworks, such as R-CNN and its successors, Fast R-CNN, and Faster R-CNN, play...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 28; no. 10; pp. 2896 - 2907 |
|---|---|
| Main Authors | , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.10.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks, such as GoogleNet and VGG, novel object detection frameworks, such as R-CNN and its successors, Fast R-CNN, and Faster R-CNN, play an essential role in improving the state of the art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this paper, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e., tubelets with convolutional neueral networks. The proposed framework won newly introduced an object-detection-from-video task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015. Code is publicly available at https://github.com/myfavouritekk/T-CNN . |
|---|---|
| AbstractList | The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks, such as GoogleNet and VGG, novel object detection frameworks, such as R-CNN and its successors, Fast R-CNN, and Faster R-CNN, play an essential role in improving the state of the art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this paper, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e., tubelets with convolutional neueral networks. The proposed framework won newly introduced an object-detection-from-video task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015. Code is publicly available at https://github.com/myfavouritekk/T-CNN . The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks, such as GoogleNet and VGG, novel object detection frameworks, such as R-CNN and its successors, Fast R-CNN, and Faster R-CNN, play an essential role in improving the state of the art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this paper, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e., tubelets with convolutional neural networks. The proposed framework won newly introduced an object-detection-from-video task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015. Code is publicly available at https://github.com/myfavouritekk/T-CNN. |
| Author | Wang, Zhe Xiao, Tong Zhang, Cong Ouyang, Wanli Zeng, Xingyu Kang, Kai Yang, Bin Wang, Xiaogang Wang, Ruohui Yan, Junjie Li, Hongsheng |
| Author_xml | – sequence: 1 givenname: Kai orcidid: 0000-0002-6707-4616 surname: Kang fullname: Kang, Kai organization: The Chinese University of Hong Kong, Hong Kong – sequence: 2 givenname: Hongsheng surname: Li fullname: Li, Hongsheng organization: The Chinese University of Hong Kong, Hong Kong – sequence: 3 givenname: Junjie surname: Yan fullname: Yan, Junjie organization: SenseTime Group Ltd., Beijing, China – sequence: 4 givenname: Xingyu surname: Zeng fullname: Zeng, Xingyu organization: SenseTime Group Ltd., Beijing, China – sequence: 5 givenname: Bin surname: Yang fullname: Yang, Bin organization: Computer Science Department, University of Toronto, Toronto, ON, Canada – sequence: 6 givenname: Tong surname: Xiao fullname: Xiao, Tong organization: The Chinese University of Hong Kong, Hong Kong – sequence: 7 givenname: Cong surname: Zhang fullname: Zhang, Cong organization: Shanghai Jiao Tong University, Shanghai, China – sequence: 8 givenname: Zhe surname: Wang fullname: Wang, Zhe organization: The Chinese University of Hong Kong, Hong Kong – sequence: 9 givenname: Ruohui surname: Wang fullname: Wang, Ruohui organization: The Chinese University of Hong Kong, Hong Kong – sequence: 10 givenname: Xiaogang surname: Wang fullname: Wang, Xiaogang organization: The Chinese University of Hong Kong, Hong Kong – sequence: 11 givenname: Wanli orcidid: 0000-0002-9163-2761 surname: Ouyang fullname: Ouyang, Wanli email: wlouyang@ee.cuhk.edu.hk organization: The Chinese University of Hong Kong, Hong Kong |
| BookMark | eNp9kD1PwzAURS0EErTwB2CxxJzi7yRsKFBAqtqhAcbIcZ5FSqiL7YD496QUMTAw3Tfc83R1Rmh_7daA0CklE0pJflEWy8dywghNJyzlSkq-h46olFnCGJH7w00kTTJG5SEahbAihIpMpEdoWSbFfH6Jy76GDmLAT218xoVbv7uuj61b6w7PofffET-cfwnYOo8X9QpMxNcQhxhqeOrdK35sG3DhGB1Y3QU4-ckxepjelMVdMlvc3hdXs8SwXMYkr3maaqqIaKxW3DTGWDBCguWsAc3STDbacCVAWGsprXOhayWBahAq1zkfo_Pd3413bz2EWK1c74fFoWKUKaE442poZbuW8S4ED7YybdTbzdHrtqsoqbYKq2-F1VZh9aNwQNkfdOPbV-0__4fOdlALAL9ARgjnhPEvzth_ng |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1016_j_eswa_2023_122240 crossref_primary_10_31466_kfbd_734393 crossref_primary_10_1631_FITEE_2100366 crossref_primary_10_1007_s11554_024_01490_0 crossref_primary_10_3390_s18030774 crossref_primary_10_1109_TCSVT_2021_3082763 crossref_primary_10_1109_TCSVT_2023_3272891 crossref_primary_10_2478_amns_2025_0600 crossref_primary_10_1109_TCSVT_2022_3183646 crossref_primary_10_1007_s00500_020_04989_3 crossref_primary_10_32604_cmc_2021_017011 crossref_primary_10_1109_TCSVT_2019_2903421 crossref_primary_10_1016_j_neucom_2024_127973 crossref_primary_10_1109_JIOT_2024_3365957 crossref_primary_10_1109_TCSVT_2021_3076523 crossref_primary_10_1080_1206212X_2018_1525929 crossref_primary_10_1155_2021_5410049 crossref_primary_10_1109_TGRS_2021_3122515 crossref_primary_10_1109_JSTARS_2021_3062176 crossref_primary_10_3390_drones8040144 crossref_primary_10_3390_electronics11213425 crossref_primary_10_1109_TCSVT_2021_3100842 crossref_primary_10_1109_TMM_2022_3164253 crossref_primary_10_3390_drones5030066 crossref_primary_10_1007_s10489_022_03529_w crossref_primary_10_1049_ipr2_12615 crossref_primary_10_2139_ssrn_4001358 crossref_primary_10_3390_urbansci7020065 crossref_primary_10_2139_ssrn_4001359 crossref_primary_10_1142_S1793962321500318 crossref_primary_10_1007_s13735_025_00355_x crossref_primary_10_1016_j_measurement_2024_115779 crossref_primary_10_1109_TIM_2023_3334348 crossref_primary_10_1016_j_imavis_2021_104238 crossref_primary_10_1109_TMM_2023_3292615 crossref_primary_10_1007_s11220_022_00399_x crossref_primary_10_1016_j_displa_2022_102230 crossref_primary_10_1109_ACCESS_2021_3138980 crossref_primary_10_1145_3606948 crossref_primary_10_1088_1742_6596_1659_1_012051 crossref_primary_10_1117_1_JEI_29_3_033015 crossref_primary_10_1145_3564663 crossref_primary_10_3390_app11104561 crossref_primary_10_1109_TAI_2024_3454566 crossref_primary_10_1109_TCSVT_2021_3094533 crossref_primary_10_1109_TCSII_2023_3241163 crossref_primary_10_1109_TCYB_2021_3114031 crossref_primary_10_1109_ACCESS_2024_3425166 crossref_primary_10_1109_TITS_2022_3176721 crossref_primary_10_1109_TVT_2020_2993863 crossref_primary_10_1016_j_image_2024_117224 crossref_primary_10_1109_TIP_2024_3364536 crossref_primary_10_3390_app122412896 crossref_primary_10_1109_TCSVT_2024_3412093 crossref_primary_10_1109_TPAMI_2021_3137605 crossref_primary_10_1186_s13634_023_01045_8 crossref_primary_10_3390_app131910578 crossref_primary_10_3390_mi13010072 crossref_primary_10_1109_TCSVT_2021_3066241 crossref_primary_10_1109_TNNLS_2021_3053249 crossref_primary_10_1155_2022_4000171 crossref_primary_10_1007_s42044_025_00242_y crossref_primary_10_1016_j_compenvurbsys_2021_101754 crossref_primary_10_1109_TGRS_2020_2978512 crossref_primary_10_1109_ACCESS_2020_3006191 crossref_primary_10_1109_TMM_2022_3150169 crossref_primary_10_26599_BDMA_2024_9020049 crossref_primary_10_1109_ACCESS_2022_3184031 crossref_primary_10_1109_TCSVT_2024_3452497 crossref_primary_10_3390_sym16030299 crossref_primary_10_1109_TCSVT_2024_3432900 crossref_primary_10_1142_S1793962323500289 crossref_primary_10_1016_j_eswa_2020_114544 crossref_primary_10_1007_s00521_022_07368_1 crossref_primary_10_3390_s22103703 crossref_primary_10_3934_mbe_2023282 crossref_primary_10_1016_j_compag_2018_09_030 crossref_primary_10_1016_j_engappai_2024_109313 crossref_primary_10_1007_s42452_019_1393_4 crossref_primary_10_1109_TPAMI_2022_3223955 crossref_primary_10_3390_app10217834 crossref_primary_10_1007_s13735_022_00263_4 crossref_primary_10_1063_5_0040424 crossref_primary_10_1016_j_bspc_2024_107206 crossref_primary_10_1007_s12652_021_03309_3 crossref_primary_10_1016_j_knosys_2025_113237 crossref_primary_10_1016_j_isprsjprs_2021_04_004 crossref_primary_10_1016_j_promfg_2020_01_289 crossref_primary_10_1061__ASCE_CP_1943_5487_0000975 crossref_primary_10_1109_ACCESS_2020_3017411 crossref_primary_10_1109_JPROC_2023_3238524 crossref_primary_10_3390_s20030578 crossref_primary_10_1007_s10055_023_00853_5 crossref_primary_10_1007_s11045_021_00764_1 crossref_primary_10_1007_s11042_020_09827_0 crossref_primary_10_1109_TITS_2024_3491784 crossref_primary_10_3390_electronics11132093 crossref_primary_10_3390_machines13020162 crossref_primary_10_3390_en17205177 crossref_primary_10_1016_j_patcog_2022_108847 crossref_primary_10_1016_j_displa_2023_102448 crossref_primary_10_1109_TGRS_2023_3278075 crossref_primary_10_1109_TGRS_2025_3534524 crossref_primary_10_3390_math10214125 crossref_primary_10_1109_ACCESS_2019_2946861 crossref_primary_10_1145_3632181 crossref_primary_10_1007_s11263_024_02201_9 crossref_primary_10_1016_j_engappai_2024_109754 crossref_primary_10_1016_j_jvcir_2023_103823 crossref_primary_10_1109_ACCESS_2025_3544515 crossref_primary_10_1016_j_imavis_2020_103929 crossref_primary_10_1016_j_neunet_2023_11_041 crossref_primary_10_1109_TCE_2023_3325480 crossref_primary_10_3390_s19091987 crossref_primary_10_3390_s23041890 crossref_primary_10_3390_rs14194833 crossref_primary_10_1088_1757_899X_711_1_012095 crossref_primary_10_1007_s00521_023_08956_5 crossref_primary_10_1016_j_future_2019_05_007 crossref_primary_10_1109_ACCESS_2022_3207282 crossref_primary_10_1061_JTEPBS_TEENG_7130 crossref_primary_10_1109_LRA_2018_2792152 crossref_primary_10_1109_TPAMI_2021_3119563 crossref_primary_10_4018_IJICTRAME_2019070102 crossref_primary_10_32604_cmc_2022_021629 crossref_primary_10_1016_j_patcog_2021_107929 crossref_primary_10_1109_TMM_2020_2990070 crossref_primary_10_1109_TCSVT_2018_2882061 crossref_primary_10_1177_14759217211010422 crossref_primary_10_3390_s21155116 crossref_primary_10_1016_j_imavis_2020_103910 crossref_primary_10_1109_TIP_2021_3099409 crossref_primary_10_1016_j_displa_2021_102020 crossref_primary_10_1109_ACCESS_2023_3328341 crossref_primary_10_3390_electronics12163421 crossref_primary_10_1016_j_ijleo_2021_168002 crossref_primary_10_1109_TCYB_2019_2894261 crossref_primary_10_1109_TCSVT_2020_2965966 crossref_primary_10_1007_s11263_021_01507_2 crossref_primary_10_1016_j_eswa_2024_124201 crossref_primary_10_1007_s11042_020_08976_6 crossref_primary_10_1109_TCSVT_2024_3350913 crossref_primary_10_1007_s10845_021_01815_x crossref_primary_10_1016_j_jfranklin_2019_11_074 crossref_primary_10_1016_j_aei_2021_101448 crossref_primary_10_1016_j_eswa_2023_122507 crossref_primary_10_1007_s11042_024_19856_8 crossref_primary_10_3390_s24092795 crossref_primary_10_1109_ACCESS_2023_3323588 crossref_primary_10_3390_s22186857 crossref_primary_10_1061__ASCE_CP_1943_5487_0000930 crossref_primary_10_1007_s11554_021_01121_y crossref_primary_10_3390_app122312314 crossref_primary_10_1016_j_neucom_2020_03_110 crossref_primary_10_1631_FITEE_2000567 crossref_primary_10_1016_j_neucom_2022_09_007 crossref_primary_10_1007_s10489_021_02838_w crossref_primary_10_1109_LSP_2023_3329419 crossref_primary_10_1007_s11042_022_13801_3 crossref_primary_10_1109_TPAMI_2019_2910529 crossref_primary_10_1109_ACCESS_2021_3120261 crossref_primary_10_17341_gazimmfd_541677 crossref_primary_10_1007_s11042_020_08977_5 crossref_primary_10_1002_stc_2857 crossref_primary_10_1109_TIM_2019_2959292 crossref_primary_10_1016_j_micpro_2020_103339 crossref_primary_10_1016_j_neucom_2024_127809 crossref_primary_10_1109_ACCESS_2024_3489714 crossref_primary_10_3390_electronics13010230 crossref_primary_10_1016_j_imavis_2019_10_007 crossref_primary_10_1109_TCSVT_2024_3421988 crossref_primary_10_1080_03772063_2020_1729258 crossref_primary_10_1007_s11042_023_17949_4 crossref_primary_10_1016_j_jiixd_2024_08_002 crossref_primary_10_2139_ssrn_4015043 crossref_primary_10_1109_MGRS_2021_3115137 crossref_primary_10_3390_electronics13204097 crossref_primary_10_1007_s00138_023_01504_0 crossref_primary_10_1016_j_patcog_2022_108544 crossref_primary_10_3390_app11031096 crossref_primary_10_1088_1742_6596_1827_1_012178 crossref_primary_10_1109_TCSVT_2024_3464631 crossref_primary_10_1007_s11554_022_01253_9 crossref_primary_10_1109_JBHI_2021_3084962 crossref_primary_10_3390_jmse12040643 crossref_primary_10_1109_TNNLS_2020_3043099 crossref_primary_10_1109_TCSVT_2018_2872575 crossref_primary_10_1007_s11263_021_01569_2 crossref_primary_10_1109_ACCESS_2022_3203399 crossref_primary_10_1007_s11760_025_03837_x crossref_primary_10_1109_TMM_2023_3241548 crossref_primary_10_1042_BST20191048 crossref_primary_10_1145_3463530 crossref_primary_10_1007_s10489_022_03463_x crossref_primary_10_1109_JSTARS_2024_3359252 crossref_primary_10_1109_TPAMI_2019_2957464 crossref_primary_10_1109_TCAD_2020_2966451 crossref_primary_10_1002_cpe_6517 crossref_primary_10_1109_TCSVT_2020_2980876 crossref_primary_10_1016_j_cviu_2021_103188 crossref_primary_10_1016_j_engappai_2024_109609 crossref_primary_10_1109_ACCESS_2019_2939201 crossref_primary_10_2139_ssrn_4196888 crossref_primary_10_1109_TPAMI_2024_3449994 crossref_primary_10_1016_j_neucom_2020_05_027 crossref_primary_10_1109_ACCESS_2020_3004992 crossref_primary_10_1109_ACCESS_2022_3165835 crossref_primary_10_1016_j_jksuci_2019_09_012 crossref_primary_10_1007_s11042_022_12715_4 crossref_primary_10_1088_1742_6596_1682_1_012012 crossref_primary_10_1007_s12652_019_01575_w crossref_primary_10_1109_TCSVT_2023_3238818 |
| Cites_doi | 10.1007/s11263-013-0620-5 10.1109/ICCV.2015.135 10.1007/978-3-319-46448-0_2 10.1109/CVPR.2015.7298594 10.1109/CVPR.2014.170 10.1109/ICCV.2015.169 10.1109/TCSVT.2008.928221 10.1109/ICCV.2013.223 10.1109/TCSVT.2016.2589879 10.1109/TCSVT.2007.903781 10.1007/978-3-642-15561-1_33 10.1109/CVPR.2015.7298675 10.1007/978-3-319-46478-7_22 10.1109/CVPR.2015.7298632 10.1109/CVPR.2015.7299146 10.1109/CVPR.2014.81 10.1109/CVPR.2017.101 10.1109/CVPR.2014.276 10.1109/CVPR.2016.90 10.1109/ICCV.2015.232 10.1109/CVPR.2016.95 10.1109/TCSVT.2005.844447 10.1109/ICCV.2015.357 10.1007/978-3-319-10578-9_48 10.1109/TCSVT.2009.2020252 10.1109/TIP.2017.2651367 10.1109/CVPR.2015.7298854 10.1109/CVPR.2016.650 10.1109/CVPR.2015.7298965 10.1109/CVPR.2012.6248065 10.1007/978-3-319-10602-1_26 10.1109/ICCV.2015.363 10.1109/CVPR.2016.235 10.1109/CVPR.2015.7298641 10.1109/CVPR.2009.5206848 10.1109/CVPR.2016.91 10.1007/978-3-319-10599-4_17 10.1109/CVPR.2013.253 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2017.2736553 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Xplore Digital Library CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore Digital Library url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 2907 |
| ExternalDocumentID | 10_1109_TCSVT_2017_2736553 8003302 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61371192 funderid: 10.13039/501100001809 – fundername: Office of Naval Research grantid: N00014-15-1-2356 funderid: 10.13039/100000006 – fundername: Hong Kong Innovation and Technology Support Programme grantid: ITS/121/15FX – fundername: SenseTime Group Ltd. – fundername: China Postdoctoral Science Foundation grantid: 2014M552339 funderid: 10.13039/501100002858 – fundername: General Research Fund through the Research Grants Council of Hong Kong grantid: CUHK14213616; CUHK14206114; CUHK14205615; CUHK419412; CUHK14203015; CUHK14239816; CUHK14207814 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION RIG 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c295t-9b377a1604dfa63cdccfec45ef32dea2785dac364e4fff11b94ab65e1ae469a93 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Mon Jun 30 04:34:17 EDT 2025 Thu Apr 24 23:07:11 EDT 2025 Tue Jul 01 00:41:10 EDT 2025 Wed Aug 27 02:52:23 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c295t-9b377a1604dfa63cdccfec45ef32dea2785dac364e4fff11b94ab65e1ae469a93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-6707-4616 0000-0002-9163-2761 |
| PQID | 2126463236 |
| PQPubID | 85433 |
| PageCount | 12 |
| ParticipantIDs | crossref_citationtrail_10_1109_TCSVT_2017_2736553 proquest_journals_2126463236 ieee_primary_8003302 crossref_primary_10_1109_TCSVT_2017_2736553 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2018-10-01 |
| PublicationDateYYYYMMDD | 2018-10-01 |
| PublicationDate_xml | – month: 10 year: 2018 text: 2018-10-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| PublicationYear | 2018 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref15 ref14 ref11 li (ref41) 2017 krizhevsky (ref30) 2012 nam (ref43) 2015 ref17 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref42 ref44 sermanet (ref10) 2013 bell (ref16) 2015 han (ref20) 2016 ref8 ref9 ref4 ref3 ref6 ref40 ref35 ref34 ref37 ref36 ref31 ren (ref5) 2015 ref33 simonyan (ref2) 2015 ref1 ref39 ref38 ioffe (ref7) 2015 ref24 maxime (ref27) 2015 ref23 ref26 zeng (ref47) 2015 ref25 ref22 ref21 ref28 simonyan (ref32) 2014 ref29 szegedy (ref49) 2016 |
| References_xml | – ident: ref45 doi: 10.1007/s11263-013-0620-5 – ident: ref13 doi: 10.1109/ICCV.2015.135 – ident: ref19 doi: 10.1007/978-3-319-46448-0_2 – ident: ref1 doi: 10.1109/CVPR.2015.7298594 – year: 2015 ident: ref47 publication-title: Window-object relationship guided representation learning for generic object detections – ident: ref34 doi: 10.1109/CVPR.2014.170 – year: 2015 ident: ref16 publication-title: Inside-Outside Net Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks – ident: ref4 doi: 10.1109/ICCV.2015.169 – ident: ref38 doi: 10.1109/TCSVT.2008.928221 – ident: ref24 doi: 10.1109/ICCV.2013.223 – year: 2013 ident: ref10 publication-title: Overfeat Integrated Recognition Localization and Detection Using Convolutional Networks – ident: ref31 doi: 10.1109/TCSVT.2016.2589879 – ident: ref37 doi: 10.1109/TCSVT.2007.903781 – ident: ref50 doi: 10.1007/978-3-642-15561-1_33 – ident: ref36 doi: 10.1109/CVPR.2015.7298675 – ident: ref48 doi: 10.1007/978-3-319-46478-7_22 – ident: ref35 doi: 10.1109/CVPR.2015.7298632 – ident: ref17 doi: 10.1109/CVPR.2015.7299146 – ident: ref3 doi: 10.1109/CVPR.2014.81 – ident: ref22 doi: 10.1109/CVPR.2017.101 – ident: ref11 doi: 10.1109/CVPR.2014.276 – ident: ref6 doi: 10.1109/CVPR.2016.90 – ident: ref15 doi: 10.1109/ICCV.2015.232 – ident: ref51 doi: 10.1109/CVPR.2016.95 – ident: ref39 doi: 10.1109/TCSVT.2005.844447 – start-page: 568 year: 2014 ident: ref32 article-title: Two-stream convolutional networks for action recognition in videos publication-title: Proc Conf Neural Inf Process Syst – ident: ref42 doi: 10.1109/ICCV.2015.357 – ident: ref9 doi: 10.1007/978-3-319-10578-9_48 – year: 2015 ident: ref7 publication-title: Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift – year: 2015 ident: ref43 publication-title: Learning multi-domain convolutional neural networks for visual tracking – ident: ref40 doi: 10.1109/TCSVT.2009.2020252 – ident: ref21 doi: 10.1109/TIP.2017.2651367 – ident: ref8 doi: 10.1109/CVPR.2015.7298854 – year: 2016 ident: ref49 publication-title: Inception-v4 inception-resnet and the impact of residual connections on learning – ident: ref44 doi: 10.1109/CVPR.2016.650 – ident: ref33 doi: 10.1109/CVPR.2015.7298965 – start-page: 685 year: 2015 ident: ref27 article-title: Is object localization for free?-Weakly-supervised learning with convolutional neural networks publication-title: Proc Comput Vis Pattern Recognit – ident: ref23 doi: 10.1109/CVPR.2012.6248065 – ident: ref46 doi: 10.1007/978-3-319-10602-1_26 – year: 2015 ident: ref2 article-title: Very deep convolutional networks for large-scale image recognition publication-title: Proc Int Conf Learn Represent – ident: ref26 doi: 10.1109/ICCV.2015.363 – ident: ref18 doi: 10.1109/CVPR.2016.235 – year: 2016 ident: ref20 publication-title: Seq-nms for video object detection – ident: ref14 doi: 10.1109/CVPR.2015.7298641 – ident: ref29 doi: 10.1109/CVPR.2009.5206848 – start-page: 1097 year: 2012 ident: ref30 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc NIPS – ident: ref12 doi: 10.1109/CVPR.2016.91 – ident: ref25 doi: 10.1007/978-3-319-10599-4_17 – start-page: 91 year: 2015 ident: ref5 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: Proc NIPS – start-page: 4126 year: 2017 ident: ref41 article-title: Learning patch-based dynamic graph for visual tracking publication-title: Proc AAAI – ident: ref28 doi: 10.1109/CVPR.2013.253 |
| SSID | ssj0014847 |
| Score | 2.6791697 |
| Snippet | The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2896 |
| SubjectTerms | Artificial neural networks computer vision Convolutional codes Image detection Machine learning Neural networks Object detection Object recognition Proposals State of the art Target tracking Training Trucks Videos |
| Title | T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos |
| URI | https://ieeexplore.ieee.org/document/8003302 https://www.proquest.com/docview/2126463236 |
| Volume | 28 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwELaAU3vgUVqxFJAPvUGW-BmHG9p2hSqxPRAot8iPsUAtCWKzPfTX13ayK2irqqfk4IkszzjfjD3zDUIfaGks9d5n3rkQoABRmVZUZ4UlWgQ49MbEc8jLmby45p9vxe0aOlnVwgBASj6DcXxNd_mutYt4VHaqYuexyBy5HgK3vlZrdWPAVWomFtwFkqmAY8sCmbw8rSZXN1XM4irGAaylEOwFCKWuKn_8ihO-TLfQ5XJmfVrJt_GiM2P78zfSxv-d-jbaHBxNfN5bxg5ag-YNev2MfnAXXVXZZDY7w9XCBPDp5vjrfXeHJ23zY7DHIB_JO9IjZYvPcfBx8RcTD2_wR-hSHleDp0_tA765d9DO36Lr6adqcpENTRYyS0vRZaVhRaGJzLnzWjLrrPVguQDPqANNCyWctkxy4EGlhJiSayMFEA0hstYle4c2mraBPYS9VN7J3NHCa840VULnwJUJkAdF6YoRIstVr-3AQB4bYXyvUySSl3XSVB01VQ-aGqHjlcxjz7_xz9G7celXI4dVH6GDpXLrYYvO64DZkktGmdz_u9R79Cp8uye_JQdoo3tawGHwQDpzlEzvFw9k2BM |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELaqcigcgFIQC4X6wK1kGz_jcEMLqy10l0PT0lvkx1hUQIK6WQ78emwnu4JSVZySg61YM3a-mfHMNwi9oqWx1HufeeeCgwJEZVpRnRWWaBHg0BsT45DzhZyd8Q8X4mILvd7UwgBASj6DcXxNd_mutasYKjtSsfNYZI68E3BfkL5aa3NnwFVqJxYMBpKpgGTrEpm8PKomp-dVzOMqxgGupRDsLxhKfVX--RknhJk-QPP12vrEkq_jVWfG9tc12sb_XfxDdH8wNfHbfm_soi1oHqF7fxAQ7qHTKpssFm9wtTIBfrol_nzZfcGTtvk57MgwP9J3pEfKF1_iYOXiTyaGb_A76FImV4OnV-13fH7poF0-RmfT99Vklg1tFjJLS9FlpWFFoYnMufNaMuus9WC5AM-oA00LJZy2THLgQamEmJJrIwUQDcG31iV7grabtoGnCHupvJO5o4XXnGmqhM6BKxNAD4rSFSNE1lKv7cBBHlthfKuTL5KXddJUHTVVD5oaocPNnB89A8eto_ei6DcjB6mP0P5aufVwSJd1QG3JJaNMPrt51gHamVXzk_rkePHxObobvtNT4ZJ9tN1dreBFsEc68zJtw99_XNtc |
| 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=T-CNN%3A+Tubelets+With+Convolutional+Neural+Networks+for+Object+Detection+From+Videos&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Kang%2C+Kai&rft.au=Li%2C+Hongsheng&rft.au=Yan%2C+Junjie&rft.au=Zeng%2C+Xingyu&rft.date=2018-10-01&rft.pub=IEEE&rft.issn=1051-8215&rft.volume=28&rft.issue=10&rft.spage=2896&rft.epage=2907&rft_id=info:doi/10.1109%2FTCSVT.2017.2736553&rft.externalDocID=8003302 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |