{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:08:41Z","timestamp":1764785321071,"version":"3.37.3"},"reference-count":57,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112100"],"award-info":[{"award-number":["2021ZD0112100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National NSF of China","doi-asserted-by":"publisher","award":["61972022","U1936212","62120106009"],"award-info":[{"award-number":["61972022","U1936212","62120106009"]}],"id":[{"id":"10.13039\/501100001809","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.2024.3359062","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T19:01:56Z","timestamp":1706814116000},"page":"1149-1161","source":"Crossref","is-referenced-by-count":10,"title":["Multimodal Composition Example Mining for Composed Query Image Retrieval"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-4513","authenticated-orcid":false,"given":"Gangjian","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-9571","authenticated-orcid":false,"given":"Shikun","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3803-9763","authenticated-orcid":false,"given":"Shikui","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-310X","authenticated-orcid":false,"given":"Shiming","family":"Ge","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"given":"Na","family":"Cai","sequence":"additional","affiliation":[{"name":"HAOMO.AI Technology Company Ltd., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2421443"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00226"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475483"},{"key":"ref11","first-page":"1","article-title":"Artemis: Attention-based retrieval with text-explicit matching and implicit similarity","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Delmas"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2980231"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01046"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040854"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3029424"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref30","article-title":"Training and challenging models for text-guided fashion image retrieval","author":"Dodds","year":"2022","journal-title":"arXiv:2204.11004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2913513"},{"key":"ref33","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532047"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_45"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2948472"},{"key":"ref41","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref42","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2020","journal-title":"arXiv:2010.00747"},{"key":"ref43","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref44","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref45","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref49","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref50","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref51","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref52","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref53","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref55","article-title":"Contrastive vision-language pre-training with limited resources","author":"Cui","year":"2021","journal-title":"arXiv:2112.09331"},{"key":"ref56","article-title":"Augmenting data with mixup for sentence classification: An empirical study","author":"Guo","year":"2019","journal-title":"arXiv:1905.08941"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10418785.pdf?arnumber=10418785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T10:02:22Z","timestamp":1709460142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3359062","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2024]]}}}