{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:09:49Z","timestamp":1775596189690,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62477010"],"award-info":[{"award-number":["62477010"]}],"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":["62577022"],"award-info":[{"award-number":["62577022"]}],"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":["62307028"],"award-info":[{"award-number":["62307028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Shanghai","award":["23ZR1441800"],"award-info":[{"award-number":["23ZR1441800"]}]},{"name":"Shanghai Science and Technology Innovation Action Plan","award":["24YF2710100"],"award-info":[{"award-number":["24YF2710100"]}]},{"name":"Shanghai Science and Technology Innovation Action Plan","award":["23YF1426100"],"award-info":[{"award-number":["23YF1426100"]}]},{"name":"Shanghai Qiji Zhifeng Company Ltd","award":["2025-GZL-RGZN-01001"],"award-info":[{"award-number":["2025-GZL-RGZN-01001"]}]},{"name":"Opening Funding of the State Key Laboratory of Disaster Reduction in Civil Engineering","award":["SLDRCE24-03"],"award-info":[{"award-number":["SLDRCE24-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3637303","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:44:43Z","timestamp":1764355483000},"page":"4885-4899","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Momentum Mixture-of-Experts for Continual Visual Question Answering"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3573-9962","authenticated-orcid":false,"given":"Tianyu","family":"Huai","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2589-0164","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5602-1877","authenticated-orcid":false,"given":"Qin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9307-3548","authenticated-orcid":false,"given":"Qingchun","family":"Bai","sequence":"additional","affiliation":[{"name":"Center of Open Distance Education, Shanghai Open University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ze","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang Zhuiqingting Technology Company Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7163-5247","authenticated-orcid":false,"given":"Xipeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4723-5486","authenticated-orcid":false,"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref2","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. NIPS","author":"Akbari"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25414"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3705725"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5981"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01620"},{"key":"ref11","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3551612"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01831"},{"key":"ref15","article-title":"Learning without forgetting for vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv:2305.19270"},{"key":"ref16","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Cho"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref18","article-title":"Continual learning with tiny episodic memories","volume-title":"Proc. Workshop Multi-Task Lifelong Reinforcement Learn.","author":"Chaudhry"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref21","first-page":"53366","article-title":"NExT-GPT: Any-to-any multimodal LLM","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref22","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. NeurIPS","author":"Ouyang"},{"key":"ref23","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref24","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref27","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref28","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref29","first-page":"4767","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452437"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454366"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3528108"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0795"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531958"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3523359"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.252"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0411"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00276"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01752"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01053"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01826"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3449109"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285221"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462734"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3443414"},{"key":"ref52","article-title":"CLAP4CLIP: Continual learning with probabilistic finetuning for vision-language models","author":"Jha","year":"2024","journal-title":"arXiv:2403.19137"},{"key":"ref53","article-title":"Class incremental learning with pre-trained vision-language models","author":"Liu","year":"2023","journal-title":"arXiv:2310.20348"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00420"},{"key":"ref55","first-page":"5383","article-title":"Lifelong language pretraining with distribution-specialized experts","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3781"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366154"},{"issue":"6","key":"ref60","first-page":"3642","article-title":"Vision and text transformer for predicting answerability on visual question answering tasks","volume":"32","author":"Shi","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382684"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00109"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.01.009"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3527032"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688270"},{"key":"ref66","article-title":"LoRAMoE: Alleviate world knowledge forgetting in large language models via MoE-style plugin","author":"Dou","year":"2023","journal-title":"arXiv:2312.09979"},{"key":"ref67","article-title":"When MOE meets LLMs: Parameter efficient fine-tuning for multi-task medical applications","author":"Liu","year":"2023","journal-title":"arXiv:2310.18339"},{"key":"ref68","article-title":"Mixture of LoRA experts","author":"Wu","year":"2024","journal-title":"arXiv:2404.13628"},{"key":"ref69","article-title":"Mixture-of-LoRAs: An efficient multitask tuning for large language models","author":"Feng","year":"2024","journal-title":"arXiv:2403.03432"},{"key":"ref70","article-title":"Retrieval-augmented mixture of LoRA experts for uploadable machine learning","author":"Zhao","year":"2024","journal-title":"arXiv:2406.16989"},{"key":"ref71","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref73","first-page":"878","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. ICLR","author":"Shazeer"},{"key":"ref74","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Du"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1844"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref78","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. NeurIPS","volume":"30","author":"Lopez-Paz"},{"key":"ref79","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"issue":"140","key":"ref80","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"JMLR"},{"key":"ref81","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang et al","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11271305.pdf?arnumber=11271305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:03:05Z","timestamp":1775592185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":82,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3637303","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}