{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:02Z","timestamp":1772907722839,"version":"3.50.1"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}],"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":["62002314"],"award-info":[{"award-number":["62002314"]}],"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":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3475510","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T17:52:25Z","timestamp":1728323545000},"page":"1615-1630","source":"Crossref","is-referenced-by-count":7,"title":["Prompting Video-Language Foundation Models With Domain-Specific Fine-Grained Heuristics for Video Question Answering"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4348-2671","authenticated-orcid":false,"given":"Ting","family":"Yu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6139-509X","authenticated-orcid":false,"given":"Kunhao","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref2","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref3","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref5","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.423"},{"key":"ref7","article-title":"StoryTrans: Non-parallel story author-style transfer with discourse representations and content enhancing","author":"Zhu","year":"2022","journal-title":"arXiv:2208.13423"},{"key":"ref8","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref9","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":"ref10","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref11","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref13","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref14","first-page":"1","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Du"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_49"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_10"},{"key":"ref17","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv:2305.16291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref22","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"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02226"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref26","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3366710"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01282"},{"key":"ref31","first-page":"5696","article-title":"OmniVL: One foundation model for image-language and video-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref34","first-page":"26462","article-title":"Learning from inside: Self-driven Siamese sampling and reasoning for video question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref35","article-title":"Youku-mPLUG: A 10 million large-scale Chinese video-language dataset for pre-training and benchmarks","author":"Xu","year":"2023","journal-title":"arXiv:2306.04362"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00499"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3409453"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3264524"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390984"},{"key":"ref52","article-title":"Self-chained image-language model for video localization and question answering","author":"Yu","year":"2023","journal-title":"arXiv:2305.06988"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.455"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref56","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref59","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Lisa Li","year":"2021","journal-title":"arXiv:2101.00190"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.556"},{"key":"ref70","article-title":"CREMA: Generalizable and efficient video-language reasoning via multimodal modular fusion","author":"Yu","year":"2024","journal-title":"arXiv:2402.05889"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref73","article-title":"Semi-parametric video-grounded text generation","author":"Kim","year":"2023","journal-title":"arXiv:2301.11507"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01189-x"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350969"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00288"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref82","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref85","first-page":"1","article-title":"PAXION: Patching action knowledge in video-language foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10706923.pdf?arnumber=10706923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:47:02Z","timestamp":1740084422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":85,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3475510","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}