{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:52Z","timestamp":1774419832267,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888491","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["M3-CVC: Controllable Video Compression with Multimodal Generative Models"],"prefix":"10.1109","author":[{"given":"Rui","family":"Wan","sequence":"first","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibo","family":"Fan","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref4","article-title":"Video Quality Assessment: A Comprehensive Survey","author":"Zheng","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_32"},{"key":"ref8","article-title":"Unicorn: Unified Neural Image Compression with One Number Reconstruction","author":"Zheng","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859831"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414731"},{"key":"ref12","first-page":"1","volume-title":"A generative compression framework for low bandwidth video conference","author":"Feng"},{"key":"ref13","article-title":"When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding","author":"Zhang","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647820"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref17","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref21","author":"Chen","year":"2023","journal-title":"eine: Short-to-long video diffusion model for generative transition and prediction"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00756"},{"key":"ref23","first-page":"8748","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref26","author":"Careil","year":"2023","journal-title":"Towards image compression with perfect realism at ultra-low bitrates"},{"key":"ref27","first-page":"36","article-title":"Lossy image compression with conditional diffusion models","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"30","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888491.pdf?arnumber=10888491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:56Z","timestamp":1774416296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888491","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}