{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T13:24:49Z","timestamp":1784294689274,"version":"3.55.0"},"reference-count":119,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"HPC resources of IDRIS","award":["2020-101267"],"award-info":[{"award-number":["2020-101267"]}]},{"name":"Google gift"},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-19-P3IA-0001"],"award-info":[{"award-number":["ANR-19-P3IA-0001"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Louis Vuitton ENS Chair on Artificial Intelligence"},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["CZ.02.1.01\/0.0\/0.0\/15 003\/0000468"],"award-info":[{"award-number":["CZ.02.1.01\/0.0\/0.0\/15 003\/0000468"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2022.3173208","type":"journal-article","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T19:59:35Z","timestamp":1652126375000},"page":"3202-3218","source":"Crossref","is-referenced-by-count":17,"title":["Learning to Answer Visual Questions From Web Videos"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7258-571X","authenticated-orcid":false,"given":"Antoine","family":"Yang","sequence":"first","affiliation":[{"name":"Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine","family":"Miech","sequence":"additional","affiliation":[{"name":"DeepMind, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Prague, Czechia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7072-3325","authenticated-orcid":false,"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"Inria Paris and Département d'informatique de l'ENS, CNRS, PSL Research University, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1620"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.302"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref12","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref13","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref15","first-page":"4352","article-title":"LifeQA: A real-life dataset for video question answering","volume-title":"Proc. 12th Int. Conf. Lang. Resour. Eval., Conf. Proc.","author":"Castro"},{"key":"ref16","first-page":"1","article-title":"iPerceive: Applying common-sense reasoning to multi-modal dense video captioning and video question answering","volume-title":"Proc. Winter Conf. Appl. Comput. Vis.","author":"Chadha"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5821"},{"key":"ref18","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16203"},{"key":"ref22","first-page":"5450","article-title":"TutorialVQA: Question answering dataset for tutorial videos","volume-title":"Proc. Int. Conf. Lang. Resour. Eval., Conf. Proc.","author":"Colas"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533961"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00536"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref29","first-page":"3543","article-title":"The IWSLT 2011 evaluation campaign on automatic talk translation","volume-title":"Proc. Int. Conf. Lang. Resour. Eval., Conf. Proc.","author":"Federico"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref35","first-page":"609","article-title":"Good question! Statistical ranking for question generation","volume-title":"Proc. Conf. Assoc. Comput. Linguistics","author":"Heilman"},{"key":"ref36","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00569"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref40","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076556"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.435"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/280"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17556"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207580"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref57","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00693"},{"key":"ref63","article-title":"Transformer-based end-to-end question generation","author":"Lopez","year":"2020"},{"key":"ref64","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref66","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref67","article-title":"UniViLM: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.312"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref73","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref74","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref76","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.196"},{"key":"ref78","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240563"},{"issue":"56","key":"ref84","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":"ref85","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref86","article-title":"Contrastive bidirectional transformer for temporal representation learning","author":"Sun","year":"2019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref90","article-title":"Zero-shot visual question answering","author":"Teney","year":"2016"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1517"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01039"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107248"},{"key":"ref95","article-title":"On modality bias in the TVQA dataset","author":"Winterbottom","year":"2020"},{"key":"ref96","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref99","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2859820"},{"key":"ref103","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00171","article-title":"Just ask: Learning to answer questions from millions of narrated videos","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Yang"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093596"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/632"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"ref108","article-title":"Learning from inside: Self-driven siamese sampling and reasoning for video question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00901"},{"key":"ref111","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73618-1_56"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3366710"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10958761\/09770842.pdf?arnumber=9770842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T18:19:18Z","timestamp":1744654758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9770842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":119,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3173208","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}