{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:33Z","timestamp":1777865313359,"version":"3.51.4"},"reference-count":70,"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":"NSFC","doi-asserted-by":"publisher","award":["92470202,U21A20471"],"award-info":[{"award-number":["92470202,U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004190","name":"Guangdong NSF","doi-asserted-by":"publisher","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}],"id":[{"id":"10.13039\/501100004190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018919","name":"PCL","doi-asserted-by":"publisher","award":["PCL2024A06"],"award-info":[{"award-number":["PCL2024A06"]}],"id":[{"id":"10.13039\/100018919","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018599","name":"Guangdong Provincial Key Laboratory of Information Security Technology","doi-asserted-by":"publisher","award":["2023B1212060026"],"award-info":[{"award-number":["2023B1212060026"]}],"id":[{"id":"10.13039\/501100018599","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\/iccv51701.2025.02022","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21778-21788","source":"Crossref","is-referenced-by-count":0,"title":["ViSpeak: Visual Instruction Feedback in Streaming Videos"],"prefix":"10.1109","author":[{"given":"Shenghao","family":"Fu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qize","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Ming","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Xing","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun-Yu","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihan","family":"Wei","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref5","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"CVPR","author":"Chen","year":"2024"},{"key":"ref8","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref10","article-title":"Moshi: a speech-text foundation model for realtime dialogue","author":"D\u00e9fossez","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref12","article-title":"Cosyvoice 2: Scalable streaming speech synthesis with large language models","author":"Du","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"ref14","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Vita: Towards open-source interactive omni multimodal 11 m","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Vita-1.5: Towards gpt-4o level real-time vision and speech interaction","author":"Fu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01396"},{"key":"ref19","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Smile: Multimodal dataset for understanding laughter in video with language models","author":"Hyun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Chatrex: Taming multimodal 11 m for joint perception and understanding","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref23","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref26","article-title":"Baichuan-omni-1.5 technical report","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Ovo-bench: How far is your videollms from real-world online video understanding?","volume-title":"CVPR","author":"Li","year":"2025"},{"key":"ref28","article-title":"Techcoach: Towards technical keypoint-aware descriptive action coaching","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp55912.2026.11463959"},{"key":"ref30","article-title":"Diversifying spatial-temporal perception for video domain generalization","volume-title":"NeurIPS","author":"Lin","year":"2023"},{"key":"ref31","article-title":"Rethinking clip-based video learners in cross-domain openvocabulary action recognition","author":"Lin","year":"2024","journal-title":"CoRR, abs\/2403.01560"},{"key":"ref32","article-title":"Humancentric transformer for domain adaptive action recognition","author":"Lin","year":"2025","journal-title":"TPAMI"},{"key":"ref33","article-title":"Et bench: Towards open-ended eventlevel video-language understanding","volume-title":"NeurIPS","author":"Liu","year":"2024"},{"key":"ref34","article-title":"Oryx mllm: On-demand spatialtemporal understanding at arbitrary resolution","volume-title":"ICLR","author":"Liu","year":"2025"},{"key":"ref35","article-title":"Ola: Pushing the frontiers of omni-modal language model with progressive modality alignment","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00349"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref39","article-title":"Actionart: Advancing multimodal large models for finegrained human-centric video understanding","author":"Peng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Streaming long video understanding with large language models","volume-title":"NeurIPS","author":"Qian","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02239"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1454"},{"key":"ref43","article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Georgiev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Qwen2 technical report","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32806"},{"key":"ref47","article-title":"Grounded-videollm: Sharpening fine-grained temporal grounding in video large language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Tarsier: Recipes for training and evaluating large video description models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","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":"ref50","article-title":"The all-seeing project v2: Towards general relation comprehension of the open world","volume-title":"ECCV","author":"Wang","year":"2024"},{"key":"ref51","article-title":"Videollm knows when to speak: Enhancing time-sensitive video comprehension with video-text duet interaction format","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_3"},{"key":"ref54","article-title":"Mini-omni2: Towards opensource gpt-4o with vision, speech and duplex capabilities","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Streaming video understanding and multi-round interaction with memoryenhanced knowledge","volume-title":"ICLR","author":"Xiong","year":"2025"},{"key":"ref56","article-title":"Slowfast-llava: A strong training-free baseline for video large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Magpie: Alignment data synthesis from scratch by prompting aligned llms with nothing","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Omniemotion: Extending video mllm with detailed face and audio modeling for multimodal emotion analysis","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Humanomniv2: From understanding to omni-modal reasoning with context","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Svbench: A benchmark with temporal multi-turn dialogues for streaming video understanding","volume-title":"ICLR","author":"Yang","year":"2025"},{"key":"ref61","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref63","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00901","article-title":"Social-iq: A question answering benchmark for artificial social intelligence","volume-title":"CVPR","author":"Zadeh","year":"2019.4"},{"key":"ref64","article-title":"Flash-vstream: Memorybased real-time understanding for long video streams","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01292"},{"key":"ref66","article-title":"Internlm-xcomposer2. 5-omnilive: A comprehensive multimodal system for long-term streaming video and audio interactions","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref69","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Humanomni: A large vision-speech language model for human-centric video understanding","author":"Zhao","year":"2025","journal-title":"arXiv preprint"}],"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\/11445571.pdf?arnumber=11445571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:13Z","timestamp":1777529713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02022","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}