{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:56:02Z","timestamp":1784300162499,"version":"3.55.0"},"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":[{"name":"National Key R&D Program of China","award":["2020AAA0140001"],"award-info":[{"award-number":["2020AAA0140001"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["21JC1400600"],"award-info":[{"award-number":["21JC1400600"]}],"id":[{"id":"10.13039\/501100003399","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.2023.3323878","type":"journal-article","created":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T17:48:08Z","timestamp":1697046488000},"page":"4554-4563","source":"Crossref","is-referenced-by-count":25,"title":["Locate Before Answering: Answer Guided Question Localization for Video Question Answering"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3881-4857","authenticated-orcid":false,"given":"Tianwen","family":"Qian","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8613-3346","authenticated-orcid":false,"given":"Ran","family":"Cui","sequence":"additional","affiliation":[{"name":"Australian National University, Canberra, ACT, Australia"}],"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4755-9736","authenticated-orcid":false,"given":"Pai","family":"Peng","sequence":"additional","affiliation":[{"name":"Bilibili Company, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1171-1956","authenticated-orcid":false,"given":"Xiaowei","family":"Guo","sequence":"additional","affiliation":[{"name":"Bilibili Company, 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":"10.1109\/CVPR.2017.149"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058248"},{"key":"ref7","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Malinowski","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3205404"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/2984875"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref38","article-title":"Layer normalization","author":"Ba","year":"2016"},{"issue":"1","key":"ref39","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref42","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3366710"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref50","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref54","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10278436.pdf?arnumber=10278436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T22:18:47Z","timestamp":1710195527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10278436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3323878","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}