{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T21:13:40Z","timestamp":1776719620834,"version":"3.51.2"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62325206"],"award-info":[{"award-number":["62325206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301276"],"award-info":[{"award-number":["62301276"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023016-4"],"award-info":[{"award-number":["BE2023016-4"]}]},{"name":"Opening Foundation of the State Key Laboratory of Tibetan Intelligence"},{"name":"Key Laboratory of Tibetan Information Processing, Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651064","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:59:40Z","timestamp":1768337980000},"page":"2772-2783","source":"Crossref","is-referenced-by-count":0,"title":["Question Understanding and Temporality Guiding for Video Question Answering"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5614-7003","authenticated-orcid":false,"given":"Jiahao","family":"Lu","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2173-1694","authenticated-orcid":false,"given":"Sisi","family":"You","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications and State Key Laboratory of Tibetan Intelligence, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications and Peng Cheng Laboratory, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613909"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612152"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref9","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":"ref10","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref11","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref20","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zellers","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref27","first-page":"11888","article-title":"ViperGPT: Visual inference via python execution for reasoning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sur","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref29","first-page":"15774","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Xue","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"ref35","article-title":"CLIP2Video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612509"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"key":"ref44","first-page":"2021","article-title":"Star: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02059"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390984"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref48","article-title":"Memory consolidation enables long-context video understanding","author":"Balaevi","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"ref50","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01272"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612577"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01275"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref57","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref58","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref63","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_11"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.455"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11348092.pdf?arnumber=11348092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:24Z","timestamp":1776715524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11348092\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651064","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}