Free-hand sketch recognition by multi-kernel feature learning
•Star graph ensemble matching is introduced to address the structure of the sketch.•MKL is employed to reach the state-of-the-art sketch recognition performance.•Sketch attributes are explored for sketch recognition and interesting applications. Free-hand sketch recognition has become increasingly p...
Saved in:
| Published in | Computer vision and image understanding Vol. 137; pp. 1 - 11 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Inc
01.08.2015
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1077-3142 1090-235X |
| DOI | 10.1016/j.cviu.2015.02.003 |
Cover
Loading…
| Abstract | •Star graph ensemble matching is introduced to address the structure of the sketch.•MKL is employed to reach the state-of-the-art sketch recognition performance.•Sketch attributes are explored for sketch recognition and interesting applications.
Free-hand sketch recognition has become increasingly popular due to the recent expansion of portable touchscreen devices. However, the problem is non-trivial due to the complexity of internal structures that leads to intra-class variations, coupled with the sparsity in visual cues that results in inter-class ambiguities. In order to address the structural complexity, a novel structured representation for sketches is proposed to capture the holistic structure of a sketch. Moreover, to overcome the visual cue sparsity problem and therefore achieve state-of-the-art recognition performance, we propose a Multiple Kernel Learning (MKL) framework for sketch recognition, fusing several features common to sketches. We evaluate the performance of all the proposed techniques on the most diverse sketch dataset to date (Mathias et al., 2012), and offer detailed and systematic analyses of the performance of different features and representations, including a breakdown by sketch-super-category. Finally, we investigate the use of attributes as a high-level feature for sketches and show how this complements low-level features for improving recognition performance under the MKL framework, and consequently explore novel applications such as attribute-based retrieval. |
|---|---|
| AbstractList | •Star graph ensemble matching is introduced to address the structure of the sketch.•MKL is employed to reach the state-of-the-art sketch recognition performance.•Sketch attributes are explored for sketch recognition and interesting applications.
Free-hand sketch recognition has become increasingly popular due to the recent expansion of portable touchscreen devices. However, the problem is non-trivial due to the complexity of internal structures that leads to intra-class variations, coupled with the sparsity in visual cues that results in inter-class ambiguities. In order to address the structural complexity, a novel structured representation for sketches is proposed to capture the holistic structure of a sketch. Moreover, to overcome the visual cue sparsity problem and therefore achieve state-of-the-art recognition performance, we propose a Multiple Kernel Learning (MKL) framework for sketch recognition, fusing several features common to sketches. We evaluate the performance of all the proposed techniques on the most diverse sketch dataset to date (Mathias et al., 2012), and offer detailed and systematic analyses of the performance of different features and representations, including a breakdown by sketch-super-category. Finally, we investigate the use of attributes as a high-level feature for sketches and show how this complements low-level features for improving recognition performance under the MKL framework, and consequently explore novel applications such as attribute-based retrieval. |
| Author | Song, Yi-Zhe Hospedales, Timothy M. Li, Yi Gong, Shaogang |
| Author_xml | – sequence: 1 givenname: Yi surname: Li fullname: Li, Yi email: yi.li@qmul.ac.uk – sequence: 2 givenname: Timothy M. surname: Hospedales fullname: Hospedales, Timothy M. email: t.hospedales@qmul.ac.uk – sequence: 3 givenname: Yi-Zhe surname: Song fullname: Song, Yi-Zhe email: yizhe.song@qmul.ac.uk – sequence: 4 givenname: Shaogang surname: Gong fullname: Gong, Shaogang email: s.gong@qmul.ac.uk |
| BookMark | eNp9kE1LAzEQhoNUsK3-AU_7B3bNJPsV0IMUq0LBi4K3kE1m27TbrCRpof_eXerJQ08zMDzv8D4zMnG9Q0LugWZAoXzYZvpoDxmjUGSUZZTyKzIFKmjKePE9GfeqSjnk7IbMQthSCpALmJKnpUdMN8qZJOww6k3iUfdrZ6PtXdKckv2hizbdoXfYJS2qePCYdKi8s259S65b1QW8-5tz8rV8-Vy8pauP1_fF8yrVPM9jKhowdYPt8F_UquClNqpUTDUl6FqxwlTAkItG8UqAQaHNcK-qhlUGkJWczwk752rfh-CxlT_e7pU_SaByFCC3chQgRwGSMjkIGKD6H6RtVGOv6JXtLqOPZxSHUkeLXgZt0Wk0dtATpentJfwXA-l52A |
| CitedBy_id | crossref_primary_10_1007_s11042_020_10033_1 crossref_primary_10_1115_1_4063760 crossref_primary_10_1016_j_patrec_2019_01_006 crossref_primary_10_3389_fnins_2016_00445 crossref_primary_10_1007_s11042_017_5514_z crossref_primary_10_1117_1_JEI_27_6_063006 crossref_primary_10_1007_s00530_016_0507_8 crossref_primary_10_1007_s10489_020_01905_y crossref_primary_10_1007_s00521_024_09836_2 crossref_primary_10_1049_cvi2_12019 crossref_primary_10_1109_TIP_2022_3160240 crossref_primary_10_1007_s11042_020_09837_y crossref_primary_10_1007_s11263_020_01382_3 crossref_primary_10_1109_TVCG_2020_2987626 crossref_primary_10_1016_j_eswa_2022_118865 crossref_primary_10_1109_TMM_2020_2966882 crossref_primary_10_1007_s10489_019_01607_0 crossref_primary_10_1016_j_eswa_2023_122505 crossref_primary_10_1109_TCDS_2020_3023055 crossref_primary_10_1016_j_jmsy_2019_12_006 crossref_primary_10_1016_j_patrec_2017_08_028 crossref_primary_10_1155_2019_6501264 crossref_primary_10_1016_j_imavis_2024_105395 crossref_primary_10_1016_j_neucom_2017_05_099 crossref_primary_10_1109_ACCESS_2019_2961368 crossref_primary_10_1007_s11042_022_12431_z crossref_primary_10_1049_ipr2_12683 crossref_primary_10_1016_j_cviu_2017_06_007 crossref_primary_10_1186_s13634_021_00752_4 crossref_primary_10_1016_j_neucom_2020_05_124 crossref_primary_10_1109_TIP_2021_3071711 crossref_primary_10_1177_1470357218759808 crossref_primary_10_1109_TMM_2020_3028466 crossref_primary_10_1371_journal_pone_0183838 crossref_primary_10_4018_IJGHPC_2018070105 crossref_primary_10_1016_j_engappai_2025_110310 crossref_primary_10_1016_j_imavis_2019_06_010 crossref_primary_10_1007_s11356_022_22584_x crossref_primary_10_1007_s11263_016_0932_3 crossref_primary_10_1155_2021_5577735 crossref_primary_10_1007_s11042_017_4368_8 crossref_primary_10_7717_peerj_cs_1186 crossref_primary_10_1007_s10111_017_0444_0 |
| Cites_doi | 10.1016/j.cad.2004.11.004 10.1016/j.jvlc.2009.12.001 10.1109/TPAMI.2005.188 10.1109/ICIME.2009.56 10.1145/1873951.1874299 10.1145/1015330.1015424 10.1109/TPAMI.2009.77 10.1109/CVPR.2013.387 10.1109/ICCV.2007.4408875 10.1016/j.cad.2009.09.004 10.1109/34.993558 10.5244/C.27.35 10.1109/CVPR.2007.383198 10.1145/1961189.1961199 10.1007/978-3-642-33718-5_45 10.1109/34.667881 10.1109/ICIP.2010.5649331 10.1109/CVPR.2005.177 10.1109/CVPR.2010.5540021 10.1145/219717.219748 10.1109/ICCV.2003.1238663 10.1109/CVPR.2006.68 10.1145/2661229.2661231 10.1109/CVPR.2011.5995353 10.1109/CVPR.2011.5995588 10.1109/ICCV.2009.5459183 10.1016/j.jvcir.2008.11.005 10.1109/CVPR.2009.5206594 10.1016/j.cag.2010.07.002 10.1109/CVPR.2013.406 10.1109/ICCVW.2009.5457691 |
| ContentType | Journal Article |
| Copyright | 2015 Elsevier Inc. |
| Copyright_xml | – notice: 2015 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.cviu.2015.02.003 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science |
| EISSN | 1090-235X |
| EndPage | 11 |
| ExternalDocumentID | 10_1016_j_cviu_2015_02_003 S1077314215000375 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMUD ADTZH AEBSH AECPX 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 CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HF~ HVGLF HZ~ IHE J1W JJJVA KOM LG5 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSV SSZ T5K TN5 XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SST |
| ID | FETCH-LOGICAL-c344t-9b1d8bef31498a536cda6a2ab61c8a25d712e39ba3791de9cdda677b27d1e2633 |
| IEDL.DBID | .~1 |
| ISSN | 1077-3142 |
| IngestDate | Tue Jul 01 04:49:31 EDT 2025 Thu Apr 24 23:11:04 EDT 2025 Fri Feb 23 02:26:56 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Attributes Multiple kernel learning Sketch recognition Ensemble matching Star graph |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c344t-9b1d8bef31498a536cda6a2ab61c8a25d712e39ba3791de9cdda677b27d1e2633 |
| OpenAccessLink | http://qmro.qmul.ac.uk/xmlui/handle/123456789/10764 |
| PageCount | 11 |
| ParticipantIDs | crossref_primary_10_1016_j_cviu_2015_02_003 crossref_citationtrail_10_1016_j_cviu_2015_02_003 elsevier_sciencedirect_doi_10_1016_j_cviu_2015_02_003 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2015-08-01 |
| PublicationDateYYYYMMDD | 2015-08-01 |
| PublicationDate_xml | – month: 08 year: 2015 text: 2015-08-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | Computer vision and image understanding |
| PublicationYear | 2015 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | M. Varma, D. Ray, Learning the discriminative power-invariance trade-off, in: ICCV, 2007, pp. 1–8. Beck, Walther, Chai, Caddigan, Fei-Fei (b0035) 2011 Tola, Lepetit, Fua (b0100) 2010; 32 Y. Cao, C. Wang, Z. Li, L. Zhang, L. Zhang, Spatial-bag-of-features, in: CVPR, 2010, pp. 3352–3359. L. Li, H. Su, Y. Lim, L. Fei-Fei, Objects as attributes for scene classification, in: ECCV, 2010. Y. Li, Y. Song, S. Gong, Sketch recognition by ensemble matching of structured features, in: British Machine Vision Conference (BMVC), 2013. R. Hu, M. Barnard, J. Collomosse, Gradient field descriptor for sketch based retrieval and localization, in: ICIP, 2010, pp. 1025–1028. Sousa, Fonseca (b0075) 2010; 21 N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, CVPR, 2005, pp. 886–893. F.R. Bach, G.R.G. Lanckreit, M.I. Jordan, Multiple kernel learning, conic duality, and the SMO algorithm, in: ICML, 2004. S. Lazebnik, C. Schmid, J. Ponce, Beyond bags of features: spatial pyramid matching for recognizing natural scene categories, in: CVPR, 2006, pp. 2169–2178. A. Vedaldi, B. Fulkerson, VLFeat: an open and portable library of computer vision algorithms, 2008 Mathias, Kristian, Tamy, Marc (b0060) 2010; 34 Y. Fu, T. Hospedales, T. Xiang, S. Gong, Learning multi-modal latent attributes, PAMI. A. Vedaldi, V. Gulshan, M. Varma, A. Zisserman, Multiple kernels for object detection, in: ICCV, 2009, pp. 606–613. Mathias, James, Marc (b0005) 2012; 31 Fonseca, Ferreira, Jorge (b0030) 2009; 41 M. Jabal, M. Rahim, N. Othman, Z. Jupri, A comparative study on extraction and recognition method of CAD data from CAD drawings, in: International Conference on Information Management and Engineering, 2009, pp. 709–713. Belongie, Malik, Puzicha (b0055) 2002; 24 E. Shechtman, M. Irani, Matching local self-similarities across images and videos, in: CVPR, 2007, pp. 1–8. Z. Sun, C. Wang, L. Zhang, L. Zhang, Free hand-drawn sketch segmentation, in: ECCV, 2012, pp. 626–639. J. Lim, C. Zitnick, P. Dollr, Sketch tokens: a learned mid-level representation for contour and object detection, in: CVPR, 2013, pp. 3158–3165. Schneider, Tuytelaars (b0205) 2014 Miller (b0120) 1995; 38 Hu, Collomosse (b0025) 2013; 117 C. Zitnick, D. Parikh, Bringing semantics into focus using visual abstraction, in: CVPR, 2013, pp. 3009–3016. Sousa, Fonsec (b0130) 2009; 20 Kittler, Hatef, Duin, Matas (b0185) 1998; 20 K. Chatfield, J. Philbin, A. Zisserman, Efficient retrieval of deformable shape classes using local self-similarities, in: Workshop on Non-rigid Shape Analysis and Deformable Image Alignment, ICCV, 2009, pp. 264–271. . J. Sivic, A. Zisserman, Video Google: a text retrieval approach to object matching in videos, in: ICCV, vol. 2, 2003, pp. 1470–1477. Mikolajczyk, Schmid (b0165) 2005; 27 Y. Cao, H. Wang, C. Wang, Z. Li, L. Zhang, L. Zhang, Mindfinder: interactive sketch-based image search on millions of images, in: International Conference on Multimedia, 2010, pp. 1605–1608. Boiman, Irani (b0180) 2007; 74 Gönen, Alpaydın (b0155) 2011; 12 Mathias, Kristian, Tamy, Marc (b0020) 2011; 17 Lu, Tai, Su, Cai (b0040) 2005; 37 Chang, Lin (b0200) 2011; 2 J. Liu, B. Kuipers, S. Savarese, Recognizing human actions by attributes, in: CVPR, 2011. F. Orabona, L. Jie, Ultra-fast optimization algorithm for sparse multi kernel learning, in: ICML, 2011, pp. 249–256. C. Lampert, H. Nickisch, S. Harmeling, Learning to detect unseen object classes by between-class attribute transfer, in: CVPR, 2009, pp. 951 – 958. Y. Cao, Z. Zhang, I. Czogiel, I. Dryden, S. Wang, 2D nonrigid partial shape matching using MCMC and contour subdivision, in: CVPR, 2011, pp. 2345–2352. 10.1016/j.cviu.2015.02.003_b0065 Sousa (10.1016/j.cviu.2015.02.003_b0130) 2009; 20 Mathias (10.1016/j.cviu.2015.02.003_b0020) 2011; 17 10.1016/j.cviu.2015.02.003_b0085 10.1016/j.cviu.2015.02.003_b0140 10.1016/j.cviu.2015.02.003_b0160 Beck (10.1016/j.cviu.2015.02.003_b0035) 2011 Belongie (10.1016/j.cviu.2015.02.003_b0055) 2002; 24 10.1016/j.cviu.2015.02.003_b0105 10.1016/j.cviu.2015.02.003_b0125 Mathias (10.1016/j.cviu.2015.02.003_b0060) 2010; 34 10.1016/j.cviu.2015.02.003_b0145 10.1016/j.cviu.2015.02.003_b0045 Gönen (10.1016/j.cviu.2015.02.003_b0155) 2011; 12 10.1016/j.cviu.2015.02.003_b0190 10.1016/j.cviu.2015.02.003_b0090 Fonseca (10.1016/j.cviu.2015.02.003_b0030) 2009; 41 Lu (10.1016/j.cviu.2015.02.003_b0040) 2005; 37 Tola (10.1016/j.cviu.2015.02.003_b0100) 2010; 32 10.1016/j.cviu.2015.02.003_b0110 Kittler (10.1016/j.cviu.2015.02.003_b0185) 1998; 20 10.1016/j.cviu.2015.02.003_b0010 10.1016/j.cviu.2015.02.003_b0175 10.1016/j.cviu.2015.02.003_b0195 Mathias (10.1016/j.cviu.2015.02.003_b0005) 2012; 31 10.1016/j.cviu.2015.02.003_b0095 10.1016/j.cviu.2015.02.003_b0150 10.1016/j.cviu.2015.02.003_b0050 10.1016/j.cviu.2015.02.003_b0170 10.1016/j.cviu.2015.02.003_b0070 Sousa (10.1016/j.cviu.2015.02.003_b0075) 2010; 21 Hu (10.1016/j.cviu.2015.02.003_b0025) 2013; 117 10.1016/j.cviu.2015.02.003_b0115 10.1016/j.cviu.2015.02.003_b0015 10.1016/j.cviu.2015.02.003_b0135 Boiman (10.1016/j.cviu.2015.02.003_b0180) 2007; 74 Miller (10.1016/j.cviu.2015.02.003_b0120) 1995; 38 Chang (10.1016/j.cviu.2015.02.003_b0200) 2011; 2 Schneider (10.1016/j.cviu.2015.02.003_b0205) 2014 10.1016/j.cviu.2015.02.003_b0080 Mikolajczyk (10.1016/j.cviu.2015.02.003_b0165) 2005; 27 |
| References_xml | – reference: C. Zitnick, D. Parikh, Bringing semantics into focus using visual abstraction, in: CVPR, 2013, pp. 3009–3016. – reference: E. Shechtman, M. Irani, Matching local self-similarities across images and videos, in: CVPR, 2007, pp. 1–8. – reference: Y. Fu, T. Hospedales, T. Xiang, S. Gong, Learning multi-modal latent attributes, PAMI. – volume: 74 start-page: 17 year: 2007 end-page: 31 ident: b0180 article-title: Detecting irregularities in images and in video publication-title: IJVC – volume: 31 start-page: 44:1 year: 2012 end-page: 44:10 ident: b0005 article-title: How do humans sketch objects? publication-title: ACM TOG (Proc. SIGGRAPH) – volume: 12 start-page: 2211 year: 2011 end-page: 2268 ident: b0155 article-title: Multiple kernel learning algorithms publication-title: J. Mach. Learn. Res. – reference: A. Vedaldi, B. Fulkerson, VLFeat: an open and portable library of computer vision algorithms, 2008, < – volume: 24 start-page: 509 year: 2002 end-page: 522 ident: b0055 article-title: Shape matching and object recognition using shape contexts publication-title: PAMI – volume: 2 start-page: 27:1 year: 2011 end-page: 27:27 ident: b0200 article-title: LIBSVM: a library for support vector machines publication-title: ACM Trans. Intell. Syst. Technol. – reference: L. Li, H. Su, Y. Lim, L. Fei-Fei, Objects as attributes for scene classification, in: ECCV, 2010. – reference: K. Chatfield, J. Philbin, A. Zisserman, Efficient retrieval of deformable shape classes using local self-similarities, in: Workshop on Non-rigid Shape Analysis and Deformable Image Alignment, ICCV, 2009, pp. 264–271. – volume: 20 start-page: 226 year: 1998 end-page: 239 ident: b0185 article-title: On combining classifiers publication-title: PAMI – reference: R. Hu, M. Barnard, J. Collomosse, Gradient field descriptor for sketch based retrieval and localization, in: ICIP, 2010, pp. 1025–1028. – volume: 41 start-page: 1067 year: 2009 end-page: 1081 ident: b0030 article-title: Sketch-based retrieval of complex drawings using hierarchical topology and geometry publication-title: Comput. Aided Des. – reference: Y. Li, Y. Song, S. Gong, Sketch recognition by ensemble matching of structured features, in: British Machine Vision Conference (BMVC), 2013. – reference: J. Liu, B. Kuipers, S. Savarese, Recognizing human actions by attributes, in: CVPR, 2011. – reference: J. Sivic, A. Zisserman, Video Google: a text retrieval approach to object matching in videos, in: ICCV, vol. 2, 2003, pp. 1470–1477. – reference: F.R. Bach, G.R.G. Lanckreit, M.I. Jordan, Multiple kernel learning, conic duality, and the SMO algorithm, in: ICML, 2004. – reference: A. Vedaldi, V. Gulshan, M. Varma, A. Zisserman, Multiple kernels for object detection, in: ICCV, 2009, pp. 606–613. – reference: Y. Cao, H. Wang, C. Wang, Z. Li, L. Zhang, L. Zhang, Mindfinder: interactive sketch-based image search on millions of images, in: International Conference on Multimedia, 2010, pp. 1605–1608. – volume: 17 start-page: 1624 year: 2011 end-page: 1636 ident: b0020 article-title: Sketch-based image retrieval: benchmark and bag-of-features descriptors publication-title: TVCG – volume: 20 start-page: 71 year: 2009 end-page: 83 ident: b0130 article-title: Geometric matching for clip-art drawing retrieval publication-title: J. Visual Commun. Image Represent. – volume: 37 start-page: 1053 year: 2005 end-page: 1069 ident: b0040 article-title: A new recognition model for electronic architectural drawings publication-title: Comput. Aided Des. – start-page: 9661 year: 2011 end-page: 9666 ident: b0035 article-title: Simple line drawings suffice for functional mri decoding of natural scene categories publication-title: Proc. Natl. Acad. Sci (PNAS) – reference: Y. Cao, Z. Zhang, I. Czogiel, I. Dryden, S. Wang, 2D nonrigid partial shape matching using MCMC and contour subdivision, in: CVPR, 2011, pp. 2345–2352. – reference: >. – reference: Z. Sun, C. Wang, L. Zhang, L. Zhang, Free hand-drawn sketch segmentation, in: ECCV, 2012, pp. 626–639. – reference: C. Lampert, H. Nickisch, S. Harmeling, Learning to detect unseen object classes by between-class attribute transfer, in: CVPR, 2009, pp. 951 – 958. – reference: S. Lazebnik, C. Schmid, J. Ponce, Beyond bags of features: spatial pyramid matching for recognizing natural scene categories, in: CVPR, 2006, pp. 2169–2178. – volume: 34 start-page: 482 year: 2010 end-page: 498 ident: b0060 article-title: An evaluation of descriptors for large-scale image retrieval from sketched feature lines publication-title: Comput. Graph. – volume: 27 start-page: 1615 year: 2005 end-page: 1630 ident: b0165 article-title: A performance evaluation of local descriptors publication-title: PAMI – reference: F. Orabona, L. Jie, Ultra-fast optimization algorithm for sparse multi kernel learning, in: ICML, 2011, pp. 249–256. – reference: M. Varma, D. Ray, Learning the discriminative power-invariance trade-off, in: ICCV, 2007, pp. 1–8. – reference: N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, CVPR, 2005, pp. 886–893. – volume: 117 start-page: 790 year: 2013 end-page: 806 ident: b0025 article-title: A performance evaluation of gradient field hog descriptor for sketch based image retrieval publication-title: CVIU – reference: M. Jabal, M. Rahim, N. Othman, Z. Jupri, A comparative study on extraction and recognition method of CAD data from CAD drawings, in: International Conference on Information Management and Engineering, 2009, pp. 709–713. – volume: 32 start-page: 815 year: 2010 end-page: 830 ident: b0100 article-title: Daisy: an efficient dense descriptor applied to wide baseline stereo publication-title: PAMI – volume: 38 start-page: 39 year: 1995 end-page: 41 ident: b0120 article-title: Wordnet: a lexical database for english publication-title: Commun. ACM – reference: J. Lim, C. Zitnick, P. Dollr, Sketch tokens: a learned mid-level representation for contour and object detection, in: CVPR, 2013, pp. 3158–3165. – reference: Y. Cao, C. Wang, Z. Li, L. Zhang, L. Zhang, Spatial-bag-of-features, in: CVPR, 2010, pp. 3352–3359. – volume: 21 start-page: 69 year: 2010 end-page: 80 ident: b0075 article-title: Sketch-based retrieval of drawings using spatial proximity publication-title: J. Visual Lang. Comput. – year: 2014 ident: b0205 article-title: Sketch classification and classification-driven analysis using fisher vectors publication-title: ACM Trans. Graph. – volume: 37 start-page: 1053 issue: 10 year: 2005 ident: 10.1016/j.cviu.2015.02.003_b0040 article-title: A new recognition model for electronic architectural drawings publication-title: Comput. Aided Des. doi: 10.1016/j.cad.2004.11.004 – volume: 17 start-page: 1624 issue: 11 year: 2011 ident: 10.1016/j.cviu.2015.02.003_b0020 article-title: Sketch-based image retrieval: benchmark and bag-of-features descriptors publication-title: TVCG – volume: 21 start-page: 69 issue: 2 year: 2010 ident: 10.1016/j.cviu.2015.02.003_b0075 article-title: Sketch-based retrieval of drawings using spatial proximity publication-title: J. Visual Lang. Comput. doi: 10.1016/j.jvlc.2009.12.001 – volume: 27 start-page: 1615 issue: 10 year: 2005 ident: 10.1016/j.cviu.2015.02.003_b0165 article-title: A performance evaluation of local descriptors publication-title: PAMI doi: 10.1109/TPAMI.2005.188 – ident: 10.1016/j.cviu.2015.02.003_b0045 doi: 10.1109/ICIME.2009.56 – ident: 10.1016/j.cviu.2015.02.003_b0015 doi: 10.1145/1873951.1874299 – ident: 10.1016/j.cviu.2015.02.003_b0140 doi: 10.1145/1015330.1015424 – volume: 32 start-page: 815 issue: 5 year: 2010 ident: 10.1016/j.cviu.2015.02.003_b0100 article-title: Daisy: an efficient dense descriptor applied to wide baseline stereo publication-title: PAMI doi: 10.1109/TPAMI.2009.77 – ident: 10.1016/j.cviu.2015.02.003_b0125 doi: 10.1109/CVPR.2013.387 – ident: 10.1016/j.cviu.2015.02.003_b0145 doi: 10.1109/ICCV.2007.4408875 – volume: 41 start-page: 1067 issue: 12 year: 2009 ident: 10.1016/j.cviu.2015.02.003_b0030 article-title: Sketch-based retrieval of complex drawings using hierarchical topology and geometry publication-title: Comput. Aided Des. doi: 10.1016/j.cad.2009.09.004 – volume: 24 start-page: 509 issue: 4 year: 2002 ident: 10.1016/j.cviu.2015.02.003_b0055 article-title: Shape matching and object recognition using shape contexts publication-title: PAMI doi: 10.1109/34.993558 – ident: 10.1016/j.cviu.2015.02.003_b0085 doi: 10.5244/C.27.35 – ident: 10.1016/j.cviu.2015.02.003_b0095 doi: 10.1109/CVPR.2007.383198 – ident: 10.1016/j.cviu.2015.02.003_b0110 – volume: 2 start-page: 27:1 year: 2011 ident: 10.1016/j.cviu.2015.02.003_b0200 article-title: LIBSVM: a library for support vector machines publication-title: ACM Trans. Intell. Syst. Technol. doi: 10.1145/1961189.1961199 – ident: 10.1016/j.cviu.2015.02.003_b0080 doi: 10.1007/978-3-642-33718-5_45 – ident: 10.1016/j.cviu.2015.02.003_b0160 – volume: 20 start-page: 226 issue: 3 year: 1998 ident: 10.1016/j.cviu.2015.02.003_b0185 article-title: On combining classifiers publication-title: PAMI doi: 10.1109/34.667881 – ident: 10.1016/j.cviu.2015.02.003_b0010 doi: 10.1109/ICIP.2010.5649331 – ident: 10.1016/j.cviu.2015.02.003_b0090 doi: 10.1109/CVPR.2005.177 – ident: 10.1016/j.cviu.2015.02.003_b0070 doi: 10.1109/CVPR.2010.5540021 – volume: 38 start-page: 39 issue: 11 year: 1995 ident: 10.1016/j.cviu.2015.02.003_b0120 article-title: Wordnet: a lexical database for english publication-title: Commun. ACM doi: 10.1145/219717.219748 – ident: 10.1016/j.cviu.2015.02.003_b0175 doi: 10.1109/ICCV.2003.1238663 – ident: 10.1016/j.cviu.2015.02.003_b0065 doi: 10.1109/CVPR.2006.68 – year: 2014 ident: 10.1016/j.cviu.2015.02.003_b0205 article-title: Sketch classification and classification-driven analysis using fisher vectors publication-title: ACM Trans. Graph. doi: 10.1145/2661229.2661231 – ident: 10.1016/j.cviu.2015.02.003_b0135 doi: 10.1109/CVPR.2011.5995353 – ident: 10.1016/j.cviu.2015.02.003_b0050 doi: 10.1109/CVPR.2011.5995588 – ident: 10.1016/j.cviu.2015.02.003_b0150 doi: 10.1109/ICCV.2009.5459183 – volume: 12 start-page: 2211 year: 2011 ident: 10.1016/j.cviu.2015.02.003_b0155 article-title: Multiple kernel learning algorithms publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.cviu.2015.02.003_b0195 – volume: 117 start-page: 790 year: 2013 ident: 10.1016/j.cviu.2015.02.003_b0025 article-title: A performance evaluation of gradient field hog descriptor for sketch based image retrieval publication-title: CVIU – volume: 20 start-page: 71 issue: 2 year: 2009 ident: 10.1016/j.cviu.2015.02.003_b0130 article-title: Geometric matching for clip-art drawing retrieval publication-title: J. Visual Commun. Image Represent. doi: 10.1016/j.jvcir.2008.11.005 – volume: 31 start-page: 44:1 issue: 4 year: 2012 ident: 10.1016/j.cviu.2015.02.003_b0005 article-title: How do humans sketch objects? publication-title: ACM TOG (Proc. SIGGRAPH) – ident: 10.1016/j.cviu.2015.02.003_b0115 – volume: 74 start-page: 17 issue: 1 year: 2007 ident: 10.1016/j.cviu.2015.02.003_b0180 article-title: Detecting irregularities in images and in video publication-title: IJVC – start-page: 9661 year: 2011 ident: 10.1016/j.cviu.2015.02.003_b0035 article-title: Simple line drawings suffice for functional mri decoding of natural scene categories publication-title: Proc. Natl. Acad. Sci (PNAS) – ident: 10.1016/j.cviu.2015.02.003_b0105 doi: 10.1109/CVPR.2009.5206594 – volume: 34 start-page: 482 issue: 5 year: 2010 ident: 10.1016/j.cviu.2015.02.003_b0060 article-title: An evaluation of descriptors for large-scale image retrieval from sketched feature lines publication-title: Comput. Graph. doi: 10.1016/j.cag.2010.07.002 – ident: 10.1016/j.cviu.2015.02.003_b0170 doi: 10.1109/CVPR.2013.406 – ident: 10.1016/j.cviu.2015.02.003_b0190 doi: 10.1109/ICCVW.2009.5457691 |
| SSID | ssj0011491 |
| Score | 2.4652672 |
| Snippet | •Star graph ensemble matching is introduced to address the structure of the sketch.•MKL is employed to reach the state-of-the-art sketch recognition... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Attributes Ensemble matching Multiple kernel learning Sketch recognition Star graph |
| Title | Free-hand sketch recognition by multi-kernel feature learning |
| URI | https://dx.doi.org/10.1016/j.cviu.2015.02.003 |
| Volume | 137 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELaqssDAo4Aoj8oDGwqtY8eOB4aqoiogukClbpHtuKi0Sqs-kFj47fgSpyoSYmCMY0vJ2bk7O999H0LXMRFWSAO_1W0rYAbUAPlIBS60E25yCSQoTn7u896APQ6jYQV1yloYgFV631_49Nxb-5amt2ZzPh43X9zGRVDCXMzKWVSg0JwxAav89msD83Dpfq6aB50D6O0LZwqMl_kYrwHeFRW8nfT34LQVcLqHaN9nirhdPMwRqtishg581oj9N7l0TaUwQ9lWQ3tbLIPH6K67sDaAE3K8nMAs4Q1qaJZh_YlzUGEwsYvMTvHI5lSf2MtJvJ2gQff-tdMLvGpCYChjq0BqksbajtzLylhFlJtUcRUqzYmJVRilgoSWSq2okCS10qTuvhA6FCmxIaf0FFWzWWbPEG5plrrNthBkZJi0TFvnIDg1REkFJyF1REpzJcZTioOyxTQpsWPvCZg4ARMnrRCISOvoZjNmXhBq_Nk7Kmch-bEsEufx_xh3_s9xF2gXrgqE3yWqrhZre-WyjpVu5MuqgXbaD0-9_jdegtWu |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07b8IwED5RGNoOfdBWpU8P3aoIHDsxGTogVBTKYylIbJHtmIqCAuJRqf--duIgKlUMXc85KTk7d2f7u-8AnuqYKRZIc62uag6VphugP-aODu3Yl2kLJFOc3Ov74ZC-jbxRAZp5LYyBVVrfn_n01FtbSdVas7qYTKrveuPCCKY6ZqUsKt4BlAw7lVeEUqPdCfvbywS9CcAZ9NAcyVHX1s5kMC_5NdkYhJeXUXeSv-PTTsxpncGJTRZRI3ufcyiopAynNnFE9rdcaVHemyGXleF4h2jwAl5aS6Ucc0iOVlMzUWgLHJonSHyjFFfoTNUyUTM0VinbJ7IdJT4uYdh6HTRDxzZOcCShdO0EAsd1ocb6Y4M694gvY-5zlwsfyzp3vZhhV5FAcMICHKtAxnqcMeGyGCvXJ-QKisk8UdeAaoLGer_NGB5LGigqlPYRPpGYB9wchlQA5-aKpGUVN80tZlEOH_uMjIkjY-Ko5hou0go8b3UWGafG3qe9fBaiXysj0k5_j97NP_Ue4TAc9LpRt93v3MKRGckAf3dQXC836l4nIWvxYBfZD7-52F8 |
| 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=Free-hand+sketch+recognition+by+multi-kernel+feature+learning&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Li%2C+Yi&rft.au=Hospedales%2C+Timothy+M.&rft.au=Song%2C+Yi-Zhe&rft.au=Gong%2C+Shaogang&rft.date=2015-08-01&rft.issn=1077-3142&rft.volume=137&rft.spage=1&rft.epage=11&rft_id=info:doi/10.1016%2Fj.cviu.2015.02.003&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cviu_2015_02_003 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon |