{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:19Z","timestamp":1777888759847,"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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62450001"],"award-info":[{"award-number":["62450001"]}],"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\/iccv51701.2025.01897","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20401-20412","source":"Crossref","is-referenced-by-count":0,"title":["VideoOrion: Tokenizing Object Dynamics in Videos"],"prefix":"10.1109","author":[{"given":"Yicheng","family":"Feng","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sipeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"BeingBeyond"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Yue","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref3","article-title":"Minigpt4-video: Advancing multimodal 11 ms for video understanding with interleaved visual-textual tokens","author":"Ataallah","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref6","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit","author":"Bird","year":"2009"},{"key":"ref7","article-title":"Temporalbench: Towards fine-grained temporal understanding for multimodal video models","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref9","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref14","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref16","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","article-title":"Open-set image tagging with multi-grained text supervision","author":"Huang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref24","article-title":"Mistral 7b","author":"Albert","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref26","article-title":"Video-lavit: Unified video-language pre-training with decoupled visual-motional tokenization","author":"Jin","year":"2024","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995378"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01471"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.31219\/osf.io\/zqxfc_v1","article-title":"Core knowledge deficits in multi-modal language models","volume-title":"Forty-second International Conference on Machine Learning","author":"Li","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref38","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3796716"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00874"},{"key":"ref45","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","author":"Mangalam","year":"2023","journal-title":"NeurIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref47","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref51","article-title":"Perception test: A diagnostic benchmark for multimodal video models","author":"Patraucean","year":"2023","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01797"},{"key":"ref54","article-title":"Artemis: Towards referential understanding in complex videos","author":"Qiu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref57","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref59","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NIPS"},{"key":"ref60","article-title":"Audio-visual 11 m for video understanding","author":"Shu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref62","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"NIPS"},{"key":"ref64","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_10"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00316"},{"key":"ref69","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"ICLR"},{"key":"ref70","article-title":"Slot-vlm: Slowfast slots for video-language modeling","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Associating objects with transformers for video object segmentation","author":"Yang","year":"2021","journal-title":"NeurIPS"},{"key":"ref73","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pretraining for open-world detection","author":"Yao","year":"2022","journal-title":"NeurIPS"},{"key":"ref74","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Merlin: Empowering multimodal 11 ms with foresight minds","author":"Yu","year":"2025","journal-title":"ECCV"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref78","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref80","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"From pixels to tokens: Byte-pair encoding on quantized visual modalities","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref83","volume-title":"Llavanext: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref84","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024","journal-title":"ICLR"},{"key":"ref85","article-title":"Tracking anything in high quality","author":"Zhu","year":"2023","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\/11445747.pdf?arnumber=11445747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:10Z","timestamp":1777611430000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01897","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}