{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:17:55Z","timestamp":1784330275328,"version":"3.55.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62032006"],"award-info":[{"award-number":["62032006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["20PJ1401900"],"award-info":[{"award-number":["20PJ1401900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3090595","type":"journal-article","created":{"date-parts":[[2021,6,23]],"date-time":"2021-06-23T19:31:01Z","timestamp":1624476661000},"page":"2914-2923","source":"Crossref","is-referenced-by-count":69,"title":["Spatial-Temporal Graphs for Cross-Modal Text2Video Retrieval"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0324-277X","authenticated-orcid":false,"given":"Xue","family":"Song","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3148-264X","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref6","first-page":"6299","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Carreira","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref9","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2912714"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2723841"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"issue":"7","key":"ref19","article-title":"Video captioning and retrieval models with semantic attention","volume":"6","author":"Yu","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref27","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Int. Conf. Learning Representations","author":"Patrick"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/140"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969787"},{"key":"ref31","first-page":"1","article-title":"Few-shot learning with graph neural networks","volume-title":"6th Int. Conf. Learning Representations","author":"Garcia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.200"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"ref36","first-page":"792","article-title":"Learning spatio-temporal structure from rgb-d videos for human activity detection and anticipation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koppula","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref39","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Int. Conf. Machine Learning","author":"Xu","year":"2018"},{"key":"ref40","article-title":"VSE: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"3rd Int. Conf. Learning Representations","author":"Kingma"},{"key":"ref44","article-title":"Learning language-visual embedding for movie understanding with natural-language","author":"Torabi"},{"key":"ref45","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume-title":"Trans. Assoc. Comput. Linguistics","author":"Kiros"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref49","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd Int. Conf. Learning Representations","author":"Simonyan"},{"key":"ref50","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"1st Int. Conf Learning Representations","author":"Mikolov"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09463746.pdf?arnumber=9463746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:21:10Z","timestamp":1705011670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9463746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3090595","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}