{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:40:36Z","timestamp":1769636436412,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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 Project","doi-asserted-by":"publisher","award":["62076096"],"award-info":[{"award-number":["62076096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Project","award":["20511100900"],"award-info":[{"award-number":["20511100900"]}]},{"name":"Shanghai Knowledge Service Platform Project","award":["ZF1213"],"award-info":[{"award-number":["ZF1213"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020002"],"award-info":[{"award-number":["LY23F020002"]}]},{"DOI":"10.13039\/501100018552","name":"Science and Technology Plan Project of Wenzhou","doi-asserted-by":"publisher","award":["LY23F020002"],"award-info":[{"award-number":["LY23F020002"]}],"id":[{"id":"10.13039\/501100018552","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3443097","type":"journal-article","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T17:42:52Z","timestamp":1723570972000},"page":"13584-13595","source":"Crossref","is-referenced-by-count":2,"title":["A Lightweight Multi-Grained Image-Text Retrieval Paradigm via Cascaded Representation Learning and Parameter-Free Feature Aggregation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1644-2733","authenticated-orcid":false,"given":"Chenyu","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9620-5665","authenticated-orcid":false,"given":"Nan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-3752","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3173131"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3034494"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207228"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref12","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref13","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Karpathy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref20","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957948"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107359"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3624016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102323"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102302"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3307288"},{"key":"ref41","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref46","volume-title":"Time Series Analysis: Forecasting and Control","author":"Box","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781139003896"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2307\/2003354"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref54","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref55","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"issue":"86","key":"ref58","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811783\/10634531.pdf?arnumber=10634531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T05:56:06Z","timestamp":1734760566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10634531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":58,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3443097","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}