{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:02Z","timestamp":1777865402467,"version":"3.51.4"},"reference-count":71,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02156","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23221-23231","source":"Crossref","is-referenced-by-count":0,"title":["ReferevErything: Towards Segmenting Everything we can Speak of in Videos"],"prefix":"10.1109","author":[{"given":"Anurag","family":"Bagchi","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Bao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Xiong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Tokmakov","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martial","family":"Hebertly","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","article-title":"Generative modeling for multi-task visual learning","author":"Bao","year":"2022","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X99002149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref6","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref8","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref9","author":"Chen","year":"2023","journal-title":"VideoCrafter1: Open diffusion models for high-quality video generation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref16","article-title":"Towards automatic concept-based explanations","author":"Ghorbani","year":"2019","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1086"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref24","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/healthcom56612.2023.10472387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00377"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref36","author":"Pont-Tuset","year":"2017","journal-title":"The 2017 DAVIS challenge on video object segmentation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00921-6"},{"key":"ref38","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref40","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2025","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref44","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref46","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref47","article-title":"Emergent correspondence from image diffusion","author":"Tang","year":"2023","journal-title":"NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02187"},{"key":"ref49","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref50","author":"Wan","year":"2025","journal-title":"Wan: Open and advanced large-scale video generative models"},{"key":"ref51","author":"Wang","year":"2023","journal-title":"ModelScope text-to-video technical report"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref56","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00289"},{"key":"ref58","article-title":"Pixelaligned language model","author":"Xu","year":"2024","journal-title":"CVPR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref66","article-title":"MOTR: End-to-end multipleobject tracking with transformer","author":"Zeng","year":"2022","journal-title":"ECCV"},{"key":"ref67","article-title":"A tale of two features: Stable diffusion complements DINO for zero-shot semantic correspondence","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref69","author":"Zheng","year":"2024","journal-title":"Open-Sora: Democratizing efficient video production for all"},{"key":"ref70","author":"Zhou","year":"2024","journal-title":"Driving referring video object segmentation with vision-language pre-trained models"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_26"}],"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\/11444354.pdf?arnumber=11444354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:27:30Z","timestamp":1777530450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02156","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}