{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:28:14Z","timestamp":1784140094426,"version":"3.55.0"},"reference-count":69,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3316077","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:41:45Z","timestamp":1694799705000},"page":"3827-3841","source":"Crossref","is-referenced-by-count":8,"title":["Feature First: Advancing Image-Text Retrieval Through Improved Visual Features"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0749-4050","authenticated-orcid":false,"given":"Dongqing","family":"Wu","sequence":"first","affiliation":[{"name":"School of Automation, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8675-3449","authenticated-orcid":false,"given":"Huihui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4427-3652","authenticated-orcid":false,"given":"Cang","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Automation, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1048-9384","authenticated-orcid":false,"given":"Cuili","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3344-6664","authenticated-orcid":false,"given":"Yinxuan","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Automation, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2977528"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013531"},{"key":"ref5","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref11","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548223"},{"key":"ref19","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frome","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref21","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Kiros","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463650"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01280"},{"key":"ref32","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karpathy","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.129"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463615"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531358"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xue","year":"2021"},{"key":"ref52","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref53","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref55","article-title":"HiCLIP: Contrastive language-image pretraining with hierarchy-aware attention","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Geng","year":"2023"},{"key":"ref56","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4362437","article-title":"CLIP-RR: Improved CLIP network for relation-focused cross-modal information retrieval","author":"Gong","year":"2023"},{"key":"ref57","article-title":"Structure-CLIP: Enhance multi-modal language representations with structure knowledge","author":"Huang","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21408"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.721"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3266435"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6720"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2996231"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref66","article-title":"Graph attention networks","author":"Velikovi","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10252008.pdf?arnumber=10252008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T04:01:17Z","timestamp":1710388877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10252008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3316077","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}