{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:34:26Z","timestamp":1762353266515,"version":"3.41.2"},"reference-count":45,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11871167","12271111"],"award-info":[{"award-number":["11871167","12271111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Support Plan for High-Level Talents of Guangdong Province","award":["2019TQ05X571"],"award-info":[{"award-number":["2019TQ05X571"]}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2022A1515011726"],"award-info":[{"award-number":["2022A1515011726"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Foundation of Guangdong Educational Committee","award":["2019KZDZX1023"],"award-info":[{"award-number":["2019KZDZX1023"]}]},{"name":"Project of Guangdong Province Innovative Team","award":["2020WCXTD011"],"award-info":[{"award-number":["2020WCXTD011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Wavelets Multiresolut Inf. Process."],"published-print":{"date-parts":[[2023,3]]},"abstract":"<jats:p> Zero-shot sketch-based image retrieval (ZSSBIR) aims at retrieving natural images given free hand-drawn sketches that may not appear during training. Previous approaches used semantic aligned sketch-image pairs or utilized memory expensive fusion layer for projecting the visual information to a low-dimensional subspace, which ignores the significant heterogeneous cross-domain discrepancy between highly abstract sketch and relevant image. This may yield poor performance in the training phase. To tackle this issue and overcome this drawback, we propose a Wasserstein distance-based cross-modal semantic network (WAD-CMSN) for ZSSBIR. Specifically, it first projects the visual information of each branch (sketch, image) to a common low-dimensional semantic subspace via Wasserstein distance in an adversarial training manner. Furthermore, a novel identity matching loss is employed to select useful features, which can not only capture complete semantic knowledge, but also alleviate the over-fitting phenomenon caused by the WAD-CMSN model. Experimental results on the challenging Sketchy (Extended) and TU-Berlin (Extended) datasets indicate the effectiveness of the proposed WAD-CMSN model over several competitors. <\/jats:p>","DOI":"10.1142\/s0219691322500540","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T14:30:15Z","timestamp":1668177015000},"source":"Crossref","is-referenced-by-count":3,"title":["WAD-CMSN: Wasserstein distance-based cross-modal semantic network for zero-shot sketch-based image retrieval"],"prefix":"10.1142","volume":"21","author":[{"given":"Guanglong","family":"Xu","sequence":"first","affiliation":[{"name":"School of Economics and Finance, South China University of Technology, Guangzhou 510006, P. R. China"}]},{"given":"Zhensheng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou 510006, P. R. China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8942-8668","authenticated-orcid":false,"given":"Jia","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Digital Economics, Guangdong University of Finance and Economics, Guangzhou 510320, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"issue":"7","key":"S0219691322500540BIB001","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","volume":"38","author":"Akata Z.","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"S0219691322500540BIB002","doi-asserted-by":"crossref","first-page":"2927","DOI":"10.1109\/CVPR.2015.7298911","volume-title":"Proc. 2015 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Akata Z.","year":"2015"},{"key":"S0219691322500540BIB003","first-page":"1","volume-title":"Proc. 2017 Int. Conf. Learning Representations (ICLR)","author":"Arjovsky M.","year":"2017"},{"key":"S0219691322500540BIB004","first-page":"214","volume-title":"Proc. 2017 Int. Conf. Machine Learning (ICML)","author":"Arjovsky M.","year":"2017"},{"key":"S0219691322500540BIB005","first-page":"2666","volume-title":"Proc. 2017 IEEE Int. Conf. Computer Vision (ICCV)","author":"Bucher M.","year":"2017"},{"key":"S0219691322500540BIB006","first-page":"3476","volume-title":"Proc. 2017 IEEE Int. Conf. Computer Vision (ICCV)","author":"Changpinyo S.","year":"2017"},{"key":"S0219691322500540BIB007","first-page":"1043","volume-title":"Proc. 2018 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Chen L.","year":"2018"},{"key":"S0219691322500540BIB008","first-page":"539","volume-title":"Proc. 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR)","volume":"1","author":"Chopra S.","year":"2005"},{"key":"S0219691322500540BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"S0219691322500540BIB010","doi-asserted-by":"crossref","first-page":"8892","DOI":"10.1109\/TIP.2020.3020383","volume":"29","author":"Deng C.","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"S0219691322500540BIB011","first-page":"5089","volume-title":"Proc. 2019 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Dutta A.","year":"2019"},{"key":"S0219691322500540BIB012","first-page":"9","volume-title":"Proc. 2019 the British Machine Vision Conf. (BMVC)","volume":"2","author":"Dutta T.","year":"2019"},{"key":"S0219691322500540BIB013","doi-asserted-by":"crossref","first-page":"2833","DOI":"10.1109\/TMM.2020.3017918","volume":"23","author":"Dutta T.","year":"2021","journal-title":"IEEE Trans. Multimedia"},{"key":"S0219691322500540BIB014","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-030-01231-1_2","volume-title":"Proc. 2018 the European Conf. Computer Vision (ECCV)","author":"Felix R.","year":"2018"},{"issue":"12","key":"S0219691322500540BIB015","doi-asserted-by":"crossref","first-page":"2916","DOI":"10.1109\/TPAMI.2012.193","volume":"35","author":"Gong Y.","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"S0219691322500540BIB016","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1016\/j.cviu.2013.02.005","volume":"117","author":"Hu R.","year":"2013","journal-title":"Comput. Vis. Image Underst."},{"key":"S0219691322500540BIB017","first-page":"19","volume-title":"Proc. 1997 Conf. Computational Linguistics and Speech Processing","author":"Jiang J. J.","year":"1997"},{"key":"S0219691322500540BIB018","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.eswa.2019.05.040","volume":"134","author":"Khan M. A.","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"S0219691322500540BIB019","first-page":"3174","volume-title":"Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Kodirov E.","year":"2017"},{"issue":"2605","key":"S0219691322500540BIB020","first-page":"2579","volume":"9","author":"Laurens V. D. M.","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"S0219691322500540BIB021","first-page":"2862","volume-title":"Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Liu L.","year":"2017"},{"key":"S0219691322500540BIB022","first-page":"1","volume-title":"Proc. 2019 IEEE Int. Conf. Computer Vision (ICCV)","author":"Liu Q.","year":"2019"},{"key":"S0219691322500540BIB023","first-page":"1","volume-title":"Proc. 1st Int. Conf. Learning Representations (ICLR)","author":"Mikolov T.","year":"2013"},{"key":"S0219691322500540BIB024","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"S0219691322500540BIB025","doi-asserted-by":"crossref","first-page":"2460","DOI":"10.1109\/ICIP.2016.7532801","volume-title":"2016 IEEE Int. Conf. Image Processing (ICIP)","author":"Qi Y.","year":"2016"},{"key":"S0219691322500540BIB026","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/CVPR.2016.13","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Reed S.","year":"2016"},{"key":"S0219691322500540BIB027","first-page":"2998","volume-title":"Proc. 2014 IEEE Conf. Int. Conf. Image Processing (ICIP)","author":"Saavedra J. M.","year":"2014"},{"issue":"2","key":"S0219691322500540BIB028","first-page":"7","volume-title":"Proc. 2015 the British Machine Vision Conf. (BMVC)","volume":"1","author":"Saavedra J. M.","year":"2015"},{"issue":"4","key":"S0219691322500540BIB029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925954","volume":"35","author":"Sangkloy P.","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"S0219691322500540BIB030","first-page":"3598","volume-title":"Proc. 2018 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Shen Y.","year":"2018"},{"key":"S0219691322500540BIB031","first-page":"1409.1556","volume-title":"Proc. 2014 Int. Conf. Learning Representations (ICLR)","author":"Simonyan K.","year":"2014"},{"key":"S0219691322500540BIB032","first-page":"935","volume-title":"13th Int. Conf. Neural Information Processing Systems (NeurIPS)","author":"Socher R.","year":"2013"},{"key":"S0219691322500540BIB033","first-page":"5551","volume-title":"Proc. 2017 IEEE Int. Conf. Computer Vision (ICCV)","author":"Song J.","year":"2017"},{"key":"S0219691322500540BIB034","doi-asserted-by":"crossref","first-page":"5473","DOI":"10.1145\/3474085.3475676","volume-title":"Proc. 29th ACM Int. Conf. Multimedia","author":"Tian J.","year":"2021"},{"key":"S0219691322500540BIB035","first-page":"2725","volume-title":"Proc. 2017 AAAI Conf. Artificial Intelligence (AAAI)","author":"Wang S.","year":"2017"},{"key":"S0219691322500540BIB036","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1109\/CVPR.2016.15","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Xian Y.","year":"2016"},{"issue":"9","key":"S0219691322500540BIB037","doi-asserted-by":"crossref","first-page":"4410","DOI":"10.1109\/TIP.2018.2837381","volume":"27","author":"Xu D.","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"S0219691322500540BIB038","first-page":"984","volume-title":"Proc. 29th Int. Joint Conf. Artificial Intelligence (IJCAI)","author":"Xu X.","year":"2021"},{"key":"S0219691322500540BIB039","first-page":"300","volume-title":"Proc. 2018 the European Conf. Computer Vision (ECCV)","author":"Yelamarthi S. K.","year":"2018"},{"key":"S0219691322500540BIB040","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1109\/CVPR.2016.93","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Yu Q.","year":"2016"},{"issue":"3","key":"S0219691322500540BIB041","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s11263-016-0932-3","volume":"122","author":"Yu Q.","year":"2017","journal-title":"Int. J. Comput. Vis."},{"key":"S0219691322500540BIB042","first-page":"300","volume-title":"Proc. European Conf. Computer Vision (ECCV)","author":"Yu Q.","year":"2014"},{"key":"S0219691322500540BIB043","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2467315"},{"key":"S0219691322500540BIB044","doi-asserted-by":"crossref","first-page":"6034","DOI":"10.1109\/CVPR.2016.649","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Zhang Z.","year":"2016"},{"key":"S0219691322500540BIB045","first-page":"2021","volume-title":"Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)","author":"Zhang L.","year":"2017"}],"container-title":["International Journal of Wavelets, Multiresolution and Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219691322500540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T08:04:52Z","timestamp":1672733092000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0219691322500540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":45,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["10.1142\/S0219691322500540"],"URL":"https:\/\/doi.org\/10.1142\/s0219691322500540","relation":{},"ISSN":["0219-6913","1793-690X"],"issn-type":[{"type":"print","value":"0219-6913"},{"type":"electronic","value":"1793-690X"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"article-number":"2250054"}}