{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T18:13:29Z","timestamp":1783188809112,"version":"3.54.6"},"reference-count":75,"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\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Australian Research Council's DECRA","award":["DE250100030"],"award-info":[{"award-number":["DE250100030"]}]},{"name":"DP funding scheme","award":["DP210101682"],"award-info":[{"award-number":["DP210101682"]}]},{"name":"DP funding scheme","award":["DP26010021"],"award-info":[{"award-number":["DP26010021"]}]},{"name":"DP funding scheme","award":["DP260101891"],"award-info":[{"award-number":["DP260101891"]}]},{"name":"DP funding scheme","award":["ARC LP220100390"],"award-info":[{"award-number":["ARC LP220100390"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651115","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:52Z","timestamp":1768255312000},"page":"3300-3312","source":"Crossref","is-referenced-by-count":1,"title":["Admitting Ignorance Helps the Video Question Answering Models to Answer"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8175-5381","authenticated-orcid":false,"given":"Haopeng","family":"Li","sequence":"first","affiliation":[{"name":"School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8204-5904","authenticated-orcid":false,"given":"Tom","family":"Drummond","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7147-5589","authenticated-orcid":false,"given":"Mingming","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, University of Melbourne, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"School of Physics, Maths and Computing, The University of Western Australia, Perth, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-3614","authenticated-orcid":false,"given":"Qiuhong","family":"Ke","sequence":"additional","affiliation":[{"name":"Department of Data Science & AI, Monash University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref4","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":"ref5","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref7","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303451"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00205"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00160"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref18","first-page":"20346","article-title":"Human-adversarial visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Sheng","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref23","article-title":"Answering from sure to uncertain: Uncertainty-aware curriculum learning for video question answering","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105280"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2938015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045034"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105284"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135655"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3370925"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3377636"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236776"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01189-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref43","first-page":"1","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yuksekgonul","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"ref45","first-page":"839","article-title":"RUBi: Reducing unimodal biases for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cadene","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref47","first-page":"1548","article-title":"Overcoming language priors in visual question answering with adversarial regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ramakrishnan","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_9"},{"key":"ref49","first-page":"2898","article-title":"Addressing failure prediction by learning model confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Corbire","year":"2019"},{"key":"ref50","first-page":"6234","article-title":"Combating label noise in deep learning using abstention","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Thulasidasan","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.84"},{"issue":"5","key":"ref52","first-page":"1605","article-title":"On the foundations of noise-free selective classification","volume":"11","author":"El-Yaniv","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.158"},{"key":"ref54","first-page":"2151","article-title":"SelectiveNet: A deep neural network with an integrated reject option","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Geifman","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.503"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","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":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00511"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.533"},{"key":"ref67","article-title":"Polyjuice: Automated, general-purpose counterfactual generation","author":"Wu","year":"2021"},{"issue":"8","key":"ref68","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref75","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329153.pdf?arnumber=11329153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:48:39Z","timestamp":1777405719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651115","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}