{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:59Z","timestamp":1772907779643,"version":"3.50.1"},"reference-count":53,"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\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3345172","type":"journal-article","created":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T19:37:39Z","timestamp":1703101059000},"page":"6131-6141","source":"Crossref","is-referenced-by-count":10,"title":["Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5940-0581","authenticated-orcid":false,"given":"Yi","family":"Cheng","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9572-2345","authenticated-orcid":false,"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-3454","authenticated-orcid":false,"given":"Dongyun","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7224-6726","authenticated-orcid":false,"given":"Ying","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4103-3824","authenticated-orcid":false,"given":"Joo-Hwee","family":"Lim","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969791"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237166"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051756"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref12","first-page":"7290","article-title":"Fine-grained semantically aligned vision-language pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3003592"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3390891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref22","first-page":"23634","article-title":"Merlot: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zellers","year":"2021"},{"key":"ref23","first-page":"26462","article-title":"Learning from inside: Self-driven siamese sampling and reasoning for video question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/513"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109436"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00188"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref42","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","article-title":"Bilinear Attention Networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142526"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref53","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10366866.pdf?arnumber=10366866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:05:10Z","timestamp":1712862310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10366866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3345172","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}