{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:38Z","timestamp":1792786898726,"version":"4.5.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["42394060"],"award-info":[{"award-number":["42394060"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Ant Group","id":[{"id":"https:\/\/ror.org\/00g5w7n47","id-type":"ROR","asserted-by":"crossref"}]},{"name":"School of Earth Sciences, Zhejiang University","id":[{"id":"https:\/\/ror.org\/00a2xv884","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3679059","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:53:12Z","timestamp":1774986792000},"page":"8545-8556","source":"Crossref","is-referenced-by-count":0,"title":["Rewind-Augmented Generation for Long Video Understanding"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7956-4646","authenticated-orcid":false,"given":"Jing","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2569-6387","authenticated-orcid":false,"given":"Luyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianzhou","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ant Group","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6177-3707","authenticated-orcid":false,"given":"Ming","family":"Kong","sequence":"additional","affiliation":[{"name":"Zhejiang University, and Zhejiang Key Laboratory of Geographic Information Science","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yadong","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2405-6776","authenticated-orcid":false,"given":"Qiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref2","article-title":"Introducing meta llama 3: The most capable openly available LLM to date","year":"2024"},{"key":"ref3","article-title":"GPT-4 turbo in the OpenAI API","year":"2024"},{"key":"ref4","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref6","article-title":"Llava-next: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref7","article-title":"Llava-next: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref8","article-title":"Qwen-Vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3383662"},{"key":"ref10","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref13","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref14","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024"},{"key":"ref15","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01278"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01282"},{"key":"ref29","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref32","article-title":"Memory-enhanced retrieval augmentation for long video understanding","author":"Yuan","year":"2025"},{"key":"ref33","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023"},{"key":"ref34","first-page":"2886","article-title":"Scaffolding coordinates to promote vision-language coordination in large multi-modal models","volume-title":"Proc. Int. Conf. Comput. Linguist.","author":"Lei"},{"key":"ref35","article-title":"Shikra: Unleashing multimodal LLMs referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.192"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4423"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref41","first-page":"27896","article-title":"Think before you speak: Training language models with pause tokens","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goyal"},{"key":"ref42","article-title":"Quiet-Star: Language models can teach themselves to think before speaking","author":"Zelikman","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref44","first-page":"12381","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251693"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72104-5_66"},{"key":"ref48","article-title":"GPT-4V(ision) system card","year":"2024"},{"key":"ref49","article-title":"Hello GPT-4o","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3604614"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11459136.pdf?arnumber=11459136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T19:16:21Z","timestamp":1790968581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11459136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3679059","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}