{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:29Z","timestamp":1777865369877,"version":"3.51.4"},"reference-count":85,"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\/100014717","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472104"],"award-info":[{"award-number":["62472104"]}],"id":[{"id":"10.13039\/100014717","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\/iccv51701.2025.02096","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22575-22585","source":"Crossref","is-referenced-by-count":1,"title":["Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation"],"prefix":"10.1109","author":[{"given":"Kaining","family":"Ying","sequence":"first","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangquan","family":"Jie","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv"},{"key":"ref2","article-title":"Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref4","article-title":"METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments","volume-title":"Assoc. Comput. Linguist. Worksh.","author":"Banerjee","year":"2005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00132"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01719"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref12","article-title":"Vision Transformer Adapter for Dense Predictions","volume-title":"Int. Conf. Learn. Represent.","author":"Chen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref15","article-title":"VideoLLaMA 2: Advancing SpatialTemporal Modeling and Audio Understanding in VideoLLMs","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Qwen2-Audio Technical Report","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref19","article-title":"Multimodal referring segmentation: A survey","author":"Ding","year":"2025","journal-title":"arXiv"},{"key":"ref20","article-title":"MOSEv2: A more challenging dataset for video object segmentation in complex scenes","author":"Ding","year":"2025","journal-title":"arXiv"},{"key":"ref21","article-title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","author":"Fu","year":"2024","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"},{"key":"ref23","volume-title":"GPT-SoVITS","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681586"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref29","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Int. Conf. Learn. Represent.","author":"Hu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02194"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680803"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i8.37542"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"ref39","article-title":"Baichuan-Omni Technical Report","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00049-8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3195"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00138"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref54","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref56","article-title":"SAM 2: Segment Anything in Images and Videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref58","article-title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","volume-title":"Int. Conf. Mach. Learn.","author":"Sun","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680802"},{"key":"ref61","article-title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","volume-title":"Int. Conf. Learn. Represent.","author":"Tang","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref63","article-title":"Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811895"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_20"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_12"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747246"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref76","article-title":"MMT- Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI","volume-title":"Int. Conf. Mach. Learn.","author":"Ying","year":"2024"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01082"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref81","article-title":"LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zeroinitialized Attention","volume-title":"Int. Conf. Learn. Represent.","author":"Zhang","year":"2024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref84","article-title":"ViLLa: Video Reasoning Segmentation with Large Language Model","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref87","article-title":"Tracking with Human-Intent Reasoning","author":"Zhu","year":"2023","journal-title":"arXiv"}],"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\/11444501.pdf?arnumber=11444501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:44Z","timestamp":1777530104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02096","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}