{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:58:55Z","timestamp":1768784335214,"version":"3.49.0"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293540"],"award-info":[{"award-number":["62293540"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293542"],"award-info":[{"award-number":["62293542"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Liaoning Province Science and Technology Plan","award":["2023JH26\/10200016"],"award-info":[{"award-number":["2023JH26\/10200016"]}]},{"DOI":"10.13039\/501100017683","name":"Dalian City Science and Technology Innovation Fund","doi-asserted-by":"publisher","award":["2023JJ11CG001"],"award-info":[{"award-number":["2023JJ11CG001"]}],"id":[{"id":"10.13039\/501100017683","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3485498","type":"journal-article","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:40:24Z","timestamp":1730396424000},"page":"6241-6252","source":"Crossref","is-referenced-by-count":5,"title":["GSSF: Generalized Structural Sparse Function for Deep Cross-Modal Metric Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4156-5417","authenticated-orcid":false,"given":"Haiwen","family":"Diao","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Holdings Ltd., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5431-1654","authenticated-orcid":false,"given":"Jiawen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/158"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/526"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref20","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9639"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6823"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"issue":"56","key":"ref33","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. IEEE Int. Conf. Mach. Learn. (PMLR)","author":"Wan"},{"key":"ref35","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref36","article-title":"Regularizing CNNs with locally constrained decorrelations","volume-title":"Proc. ICLR","author":"Rodr\u00edguez"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"ref38","first-page":"4328","article-title":"Channel redundancy and overlap in convolutional neural networks with channelwise NNK graphs","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP)","author":"Bonet"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"ref42","first-page":"1849","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. NeurIPS","author":"Sohn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref44","first-page":"4170","article-title":"Learning deep embeddings with histogram loss","volume-title":"Proc. NeurIPS","author":"Ustinova"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.283"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00655"},{"key":"ref49","article-title":"Collapse-aware triplet decoupling for adversarially robust image retrieval","volume-title":"Proc. ICML","author":"Tian"},{"key":"ref50","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"Chechik","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00516"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00659"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02365"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00316"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2018.2822810"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00495"},{"key":"ref67","first-page":"1262","article-title":"Local similarity-aware deep feature embedding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01185"},{"key":"ref69","first-page":"9410","article-title":"Learning intra-batch connections for deep metric learning","volume-title":"Proc. ICML","volume":"139","author":"Seidenschwarz"},{"key":"ref70","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. NeurIPS","author":"Huang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00254"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3384675"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3352397"},{"key":"ref74","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379752"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref77","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref80","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. NIPS","author":"Kim"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968154"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746965"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719574"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref90","article-title":"FILIP: Fine-grained interactive language-image pretraining","volume-title":"Proc. ICLR","author":"Yao"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref92","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022","journal-title":"arXiv:2203.07111"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref94","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref96","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref98","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. NeurIPS","author":"Sung"},{"key":"ref99","article-title":"UniPT: Universal parallel tuning for transfer learning with efficient parameter and memory","author":"Diao","year":"2023","journal-title":"arXiv:2308.14316"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613460"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00063"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"ref106","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume-title":"Proc. NeurIPS","author":"Lian"},{"key":"ref107","first-page":"91","article-title":"Faster R-CNN: Towards realtime object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10740591.pdf?arnumber=10740591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T06:37:51Z","timestamp":1732689471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":108,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3485498","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}