{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T18:39:29Z","timestamp":1782931169583,"version":"3.54.5"},"reference-count":55,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276106"],"award-info":[{"award-number":["62276106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02167","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23342-23352","source":"Crossref","is-referenced-by-count":2,"title":["How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?"],"prefix":"10.1109","author":[{"given":"Yujian","family":"Lee","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqi","family":"Xu","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentao","family":"Fan","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47240-4_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3542995"},{"key":"ref9","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Mona: Moving object detection from videos shot by dynamic camera","author":"Hu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app14125068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/97"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref15","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Duetml: Human-llm collaborative machine learning framework for non-expert users","author":"Kawabe","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT, page 2. Minneapolis, Minnesota","author":"Devlin","year":"2019"},{"key":"ref18","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref19","first-page":"1973019742. PMLR","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i8.37542"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref24","article-title":"Audio-aware query-enhanced transformer for audio-visual segmentation","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02487"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1108\/LHTN-01-2023-0009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_19"},{"key":"ref29","article-title":"Learning modality knowledge alignment for cross-modality transfer","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Av-sam: Segment anything model meets audio-visual localization and segmentation","author":"Mo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120865"},{"key":"ref32","article-title":"Mmrel: A relation understanding dataset and benchmark in the mllm era","author":"Nie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772767"},{"key":"ref34","author":"Park","journal-title":"Save: Segment audio-visual easy way using the segment anything model"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2421"},{"key":"ref36","article-title":"Crossmodality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv preprint"},{"issue":"01","key":"ref37","article-title":"A time series image semantic segmentation model modified by optical flow","volume":"46","author":"QIU","year":"2024","journal-title":"Computer Engineering & Science"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref39","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3412743"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2024.3524120"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02562"},{"key":"ref49","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"X-vila: Cross-modality alignment for large language model","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","first-page":"4267","article-title":"Clipceil: Domain generalization through clip via channel refinement and imagetext alignment","volume":"37","author":"Yu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01800"},{"key":"ref53","article-title":"Mmllms: Recent advances in multimodal large language models","author":"Zhang","journal-title":"arxiv 2024. arXiv preprint arXiv:2401.13601"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"}],"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\/11444595.pdf?arnumber=11444595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:48Z","timestamp":1777612788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02167","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}