{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:01:09Z","timestamp":1783530069224,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62222213"],"award-info":[{"award-number":["62222213"]}],"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":["U22B2059"],"award-info":[{"award-number":["U22B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3571422","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T13:17:05Z","timestamp":1747747025000},"page":"11598-11612","source":"Crossref","is-referenced-by-count":3,"title":["Scenario-Aware Multimodal Chain-of-Thought Prompting for Rationales of VideoSocial Relations"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1538-0475","authenticated-orcid":false,"given":"Penggang","family":"Qin","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-5386","authenticated-orcid":false,"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2579-8783","authenticated-orcid":false,"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heda","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaohongshu, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiaohongshu, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, Anhui Province Key Laboratory of Big Data Analysis and Application, School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Shrikumar"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00007","volume-title":"Feature Visualization","author":"Olah","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00267"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475684"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00987"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463634"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3181849"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337838"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612175"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390742"},{"key":"ref16","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima"},{"key":"ref17","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3349567"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3444895"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462433"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02674"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref27","first-page":"3","article-title":"Event perception","volume":"1","author":"Tversky","year":"2013","journal-title":"The Oxford Handbook of Cognitive Psychology"},{"key":"ref28","article-title":"Visual chain of thought: Bridging logical gaps with multimodal infillings","author":"Rose","year":"2023","journal-title":"arXiv:2305.02317"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/1089-2680.2.2.175"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.130.1.29"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_26"},{"key":"ref35","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3391304"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3397997"},{"key":"ref42","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.4135\/9781446249222.n49"},{"key":"ref48","article-title":"Balanced multimodal learning: An integrated framework for multi-task learning in audio-visual fusion","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Fu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3550900"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3524645"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29844"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11007228.pdf?arnumber=11007228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:46:59Z","timestamp":1762195619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3571422","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}