{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:26:09Z","timestamp":1770845169279,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342922","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"3108-3113","source":"Crossref","is-referenced-by-count":0,"title":["MGQA: Mixture Gaussian for Video Grounded Question Answering via VLMs"],"prefix":"10.1109","author":[{"given":"Zhixian","family":"He","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,Guangzhou,China"}]},{"given":"Xiaofan","family":"Ma","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,Guangzhou,China"}]},{"given":"Qiushi","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,Guangzhou,China"}]},{"given":"Shujin","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref4","first-page":"20729","article-title":"Paxion: Patching action knowledge in video-language foundation models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang","year":"2023"},{"key":"ref5","article-title":"Self-chained image-language model for video localization and question answering","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"issue":"140","key":"ref6","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02385-8"},{"key":"ref8","article-title":"RaVL: Discovering and mitigating spurious correlations in fine-tuned vision-language models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Varma"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32214"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref12","article-title":"Cg-bench: Clue-grounded question answering benchmark for long video understanding","author":"Chen","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680826"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729945"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"North American Chapter of the Association for Computational Linguistics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0900"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref26","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342922.pdf?arnumber=11342922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:06Z","timestamp":1770843006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342922","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}