{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:53Z","timestamp":1777865453006,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA1000102"],"award-info":[{"award-number":["2021YFA1000102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376285,61673396"],"award-info":[{"award-number":["62376285,61673396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022MF260"],"award-info":[{"award-number":["ZR2022MF260"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01706","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18357-18366","source":"Crossref","is-referenced-by-count":0,"title":["SUV: Suppressing Undesired Video Content via Semantic Modulation Based on Text Embeddings"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Lv","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, China University of Petroleum (East China),Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software, Qingdao Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, China University of Petroleum (East China),Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software, Qingdao Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingzhuang","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, China University of Petroleum (East China),Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software, Qingdao Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, China University of Petroleum (East China),Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software, Qingdao Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yecong","family":"Wan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, China University of Petroleum (East China),Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software, Qingdao Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, China University of Petroleum (East China),Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software, Qingdao Institute of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref2","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"ref7","article-title":"Flatten: optical flowguided attention for consistent text-to-video editing","volume-title":"International Conference on Learning Representations","author":"Cong","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00641"},{"key":"ref11","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","volume-title":"International Conference on Learning Representations","author":"Geyer","year":"2024"},{"key":"ref12","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref15","article-title":"Token merging for trainingfree semantic binding in text-to-image synthesis","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00639"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref19","article-title":"Video token merging for long-form video understanding","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"ref23","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"issue":"2","key":"ref26","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref32","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Cove: Unleashing the diffusion feature correspondence for consistent video editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00734"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref38","article-title":"Ipadapte: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref40","article-title":"Controlvideo: Training-free controllable text-to-video generation","volume-title":"International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref41","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_26"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444109.pdf?arnumber=11444109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:51Z","timestamp":1777530951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01706","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}