{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T02:58:04Z","timestamp":1781751484369,"version":"3.54.5"},"reference-count":81,"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":["62422606,62201484"],"award-info":[{"award-number":["62422606,62201484"]}],"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\/iccv51701.2025.02197","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23667-23677","source":"Crossref","is-referenced-by-count":1,"title":["ViLLa: Video Reasoning Segmentation with Large Language Model"],"prefix":"10.1109","author":[{"given":"Rongkun","family":"Zheng","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Qi","sequence":"additional","affiliation":[{"name":"Insta360"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref3","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref6","article-title":"How far are we to gpt-4v?","author":"Chen","year":"2024","journal-title":"closing the gap to commercial multimodal models with open-source suites"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref9","author":"Cheng","year":"2023","journal-title":"Segment and track anything"},{"key":"ref10","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 % chatgpt quality"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref14","article-title":"Vitron: A unified pixel-level vision 11 m for understanding, generating, segmenting, editing","author":"Fei","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2025","journal-title":"CVPR"},{"key":"ref16","author":"Gao","year":"2023","journal-title":"Llama-adapter v2: Parameter-efficient visual instruction model."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1679"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref25","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01247"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"ref34","author":"Liu","year":"2023","journal-title":"Interngpt: Solving vision-centric tasks by interacting with chatgpt beyond language"},{"key":"ref35","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022","journal-title":"ICLR"},{"key":"ref36","author":"Luo","year":"2023","journal-title":"Valley: Video assistant with large language model enhanced ability."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref38","article-title":"Chatgpt: A language model for conversational ai","year":"2023","journal-title":"Technical report, OpenAI"},{"key":"ref39","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref40","author":"Peng","year":"2023","journal-title":"Instruction tuning with gpt-4."},{"key":"ref41","author":"Peng","year":"2023","journal-title":"Kosmos-2: Grounding multimodal large language models to the world."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref43","author":"Qi","year":"2024","journal-title":"Generalizable entity grounding via assistance of large language model."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3462628"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610216"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01725"},{"key":"ref50","author":"Taori","year":"2023","journal-title":"Stanford alpaca: An instruction-following llama model"},{"key":"ref51","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.50"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref56","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"ICML"},{"key":"ref57","author":"Wang","year":"2024","journal-title":"Omnidrive: A holistic 11 m -agent framework for autonomous driving with 3d perception, reasoning and planning."},{"key":"ref58","author":"Wang","year":"2023","journal-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref70","author":"Yang","year":"2023","journal-title":"An improved baseline for reasoning segmentation with large language model."},{"key":"ref71","author":"Ye","year":"2023","journal-title":"mplug-owl: Modularization empowers large language models with multimodality."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref73","author":"You","year":"2023","journal-title":"Ferret: Refer and ground anything anywhere at any granularity."},{"key":"ref74","author":"Yu","year":"2022","journal-title":"Coca: Contrastive captioners are image-text foundation models."},{"key":"ref75","author":"Zhang","year":"2023","journal-title":"Llamaadapter: Efficient fine-tuning of language models with zeroinit attention."},{"key":"ref76","author":"Zhang","year":"2022","journal-title":"Opt: Open pre-trained transformer language models."},{"key":"ref77","author":"Zhang","year":"2024","journal-title":"Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref79","article-title":"Dvis-daq: Improving video segmentation via dynamic anchor queries","author":"Zhou","year":"2024","journal-title":"ECCV"},{"key":"ref80","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing visionlanguage understanding with advanced large language models."},{"key":"ref81","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"ICLR"}],"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\/11445841.pdf?arnumber=11445841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:40Z","timestamp":1777530160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02197","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}