{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:35Z","timestamp":1775578595458,"version":"3.50.1"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":"crossref","award":["62072190"],"award-info":[{"award-number":["62072190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key-Area Research and Development Program Guangdong Province","award":["2018B010107001"],"award-info":[{"award-number":["2018B010107001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202311"],"award-info":[{"award-number":["62202311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Key Project of Peng Cheng Laboratory","award":["PCL2023A08"],"award-info":[{"award-number":["PCL2023A08"]}]},{"DOI":"10.13039\/501100001809","name":"TCL Science and Technology Innovation Fund, Shenzhen Natural Science Foundation","doi-asserted-by":"publisher","award":["20220809180405001"],"award-info":[{"award-number":["20220809180405001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Excellent Science and Technology Creative Talent Training Program of Shenzhen Municipality","award":["RCBS20221008093224017"],"award-info":[{"award-number":["RCBS20221008093224017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3514820","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T03:12:56Z","timestamp":1733886776000},"page":"4592-4607","source":"Crossref","is-referenced-by-count":6,"title":["Toward Long Video Understanding via Fine-Detailed Video Story Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3808-5650","authenticated-orcid":false,"given":"Zeng","family":"You","sequence":"first","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4969-0060","authenticated-orcid":false,"given":"Zhiquan","family":"Wen","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8916-8368","authenticated-orcid":false,"given":"Yaofo","family":"Chen","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-4245","authenticated-orcid":false,"given":"Runhao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3246091"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3240464"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235523"},{"key":"ref5","first-page":"5282","article-title":"MOMA-LRG: Language-refined graphs for multi-object multi-actor activity parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Luo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3399933"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3360530"},{"key":"ref12","article-title":"VideoChat: Chat-centric video understanding","author":"Li","year":"2023","journal-title":"arXiv:2305.06355"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref14","article-title":"MovieChat: From dense token to sparse memory for long video understanding","author":"Song","year":"2023","journal-title":"arXiv:2307.16449"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319140"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287201"},{"key":"ref19","first-page":"13627","article-title":"Alignment-guided temporal attention for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25375"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref24","first-page":"279","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326692"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201540"},{"key":"ref30","first-page":"38032","article-title":"Long-form video-language pre-training with multimodal temporal contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref31","article-title":"VideoGraph: Recognizing minutes-long human activities in videos","author":"Hussein","year":"2019","journal-title":"arXiv:1905.05143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"ref34","first-page":"2846","article-title":"S4ND: Modeling images and videos as multidimensional signals with state spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Nguyen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"ref36","first-page":"1","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01257"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref42","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3390133"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02214"},{"key":"ref50","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref52","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref54","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.03191"},{"key":"ref55","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref57","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref65","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref66","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref67","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv:2307.06942"},{"key":"ref68","volume-title":"PySceneDetect","year":"2024"},{"key":"ref69","volume-title":"Decord: An Efficient Video Loader for Deep Learning","year":"2024"},{"key":"ref70","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":"ref71","first-page":"1","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612349"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_24"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21236\/ADA531042"},{"key":"ref83","first-page":"46212","article-title":"EgoSchema: A diagnostic benchmark for very long-form video language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mangalam"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref87","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"arXiv:2306.05685"},{"key":"ref88","volume-title":"ShareGPT: Share Your Wildest ChatGPT Conversations With One Click","year":"2023"},{"key":"ref89","article-title":"AnglE-optimized text embeddings","author":"Li","year":"2023","journal-title":"arXiv:2309.12871"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"ref93","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref96","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":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"ref98","first-page":"76749","article-title":"Self-chained image-language model for video localization and question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yu"},{"key":"ref99","first-page":"2527","article-title":"Memory consolidation enables long-context video understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bala\u017eevi\u0107"},{"key":"ref100","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref101","article-title":"A simple LLM framework for long-range video question-answering","author":"Zhang","year":"2023","journal-title":"arXiv:2312.17235"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref105","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":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10789221.pdf?arnumber=10789221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T17:55:27Z","timestamp":1746640527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10789221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":108,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3514820","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}