{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:37:29Z","timestamp":1786390649601,"version":"build-2736575974"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":"crossref","award":["U23B2060"],"award-info":[{"award-number":["U23B2060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2022ZD0114900"],"award-info":[{"award-number":["2022ZD0114900"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3690561","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T20:02:34Z","timestamp":1778011354000},"page":"11044-11061","source":"Crossref","is-referenced-by-count":0,"title":["IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5305-487X","authenticated-orcid":false,"given":"Jiapeng","family":"Li","sequence":"first","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8535-9527","authenticated-orcid":false,"given":"Ping","family":"Wei","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2327-0842","authenticated-orcid":false,"given":"Wenjuan","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9458-5583","authenticated-orcid":false,"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1943-287X","authenticated-orcid":false,"given":"Lifeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Institute for General Artificial Intelligence","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2022.9150010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/1416950"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(98)00058-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2006.09.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/180"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(00)01615-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.117"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413641"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref20","first-page":"11633","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.289"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01113"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02059"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-020-01730-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123364"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548061"},{"key":"ref32","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref33","first-page":"887","article-title":"Dynamic visual reasoning by learning differentiable physics models from video and language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ding","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/35086023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.07.006"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2976971"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459260"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.051"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12313"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759242"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4013382"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.248"},{"key":"ref48","article-title":"Where MLLMs attend and what they rely on: Explaining autoregressive token generation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Chen","year":"2026"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.611"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.182"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3560033"},{"key":"ref53","first-page":"19290","article-title":"Unsupervised vision-language grammar induction with shared structure modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wan","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01516"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00676"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00582"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00723"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02796"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00859"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1162\/daed_a_01906"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16792"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1243"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1454"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.61"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref66","first-page":"12585","article-title":"Less is more: Fewer interpretable region via submodular subset selection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref67","article-title":"Less is More: Efficient black-box attribution via minimal interpretable subset selection","author":"Chen","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.373"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16625"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17590"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.588"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.799"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.341"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.225"},{"key":"ref76","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref78","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":"ref79","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref80","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":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref82","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref85","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0767"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref90","article-title":"MM-REACT: Prompting ChatGPT for multimodal reasoning and action","author":"Yang","year":"2023"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref93","article-title":"Deep biaffine attention for neural dependency parsing","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Dozat","year":"2017"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref96","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Malinowski","year":"2014"},{"key":"ref97","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11506215.pdf?arnumber=11506215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:05:05Z","timestamp":1786388705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11506215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":100,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3690561","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":[[2026,9]]}}}