{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:01:25Z","timestamp":1777734085045,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62425208"],"award-info":[{"award-number":["62425208"]}],"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":["62122018"],"award-info":[{"award-number":["62122018"]}],"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":["62020106008"],"award-info":[{"award-number":["62020106008"]}],"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":["U22A2097"],"award-info":[{"award-number":["U22A2097"]}],"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":["U23A2031"],"award-info":[{"award-number":["U23A2031"]}],"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":["82441006"],"award-info":[{"award-number":["82441006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Committee of Shenzhen Municipality Foundation","award":["JCYJ20240813114208012"],"award-info":[{"award-number":["JCYJ20240813114208012"]}]},{"name":"Sichuan Science and Technology Program","award":["2023ZHYZ0004"],"award-info":[{"award-number":["2023ZHYZ0004"]}]},{"name":"Kuaishou"},{"name":"Yibin High-Level Talent Introduction Program","award":["2024YG07"],"award-info":[{"award-number":["2024YG07"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3556422","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T19:51:47Z","timestamp":1743450707000},"page":"9003-9016","source":"Crossref","is-referenced-by-count":2,"title":["Temporal-Guided Mixture-of-Experts for Zero-Shot Video Question Answering"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1067-062X","authenticated-orcid":false,"given":"Yixin","family":"Qin","sequence":"first","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8838-164X","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sichuan Artificial Intelligence Institute, Yibin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Sichuan Artificial Intelligence Institute, Yibin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng","family":"Tao Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref12","article-title":"PromptCap: Prompt-guided task-aware image captioning","author":"Hu","year":"2022","journal-title":"arXiv:2211.09699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref15","first-page":"1","article-title":"DeCap: Decoding CLIP latents for zero-shot captioning via text-only training","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00257"},{"key":"ref17","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3038784"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3026546"},{"key":"ref26","first-page":"8483","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref27","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. neural Inf. Process. Syst.","author":"Brown"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00523"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/10.623058"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3119.003.0042"},{"key":"ref31","first-page":"1","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shazeer"},{"issue":"1","key":"ref32","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref34","article-title":"Multimodal contrastive learning with LIMoE: The language-image mixture of experts","author":"Mustafa","year":"2022","journal-title":"arXiv:2206.02770"},{"key":"ref35","article-title":"Adamix: Mixture-of-adapter for parameter-efficient tuning of large language models","author":"Wang","year":"2022","journal-title":"arXiv:2205.12410"},{"key":"ref36","first-page":"1","article-title":"Sparse mixture-of-experts are domain generalizable learners","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117064"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02318"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref40","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref41","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref42","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref43","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref44","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref47","first-page":"1","article-title":"Taming sparsely activated transformer with stochastic experts","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zuo"},{"key":"ref48","first-page":"1","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"He"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref52","first-page":"1","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. 25th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Wu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref55","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref58","article-title":"HiTeA: Hierarchical temporal-aware video-language pre-training","author":"Ye","year":"2022","journal-title":"arXiv:2212.14546"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref60","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.03191"},{"key":"ref61","article-title":"Video-text modeling with zero-shot transfer from contrastive captioners","author":"Yan","year":"2022","journal-title":"arXiv:2212.04979"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref63","article-title":"CLIP2 Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref64","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv:2203.15556"},{"key":"ref65","first-page":"34600","article-title":"On the representation collapse of sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chi"},{"issue":"86","key":"ref66","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10946169.pdf?arnumber=10946169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:49:23Z","timestamp":1757526563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10946169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3556422","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}