{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:39Z","timestamp":1777865319460,"version":"3.51.4"},"reference-count":47,"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\/iccv51701.2025.02090","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22509-22518","source":"Crossref","is-referenced-by-count":0,"title":["Towards Fine-Grained Interactive Segmentation in Images and Videos"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Yao","sequence":"first","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiushi","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miaomiao","family":"Cui","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","author":"Alexey","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"Kirillov","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Wang","year":"2022","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref10","article-title":"Segment and recognize anything at any granularity","author":"Sun","year":"2024","journal-title":"ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref13","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","author":"Tai","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Segment anything in high quality","author":"Ke","year":"2023","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00294","article-title":"Fss-1000: A 1000-class dataset for fewshot segmentation","volume-title":"CVPR","author":"Li","year":"2020"},{"key":"ref18","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Schroff","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref24","article-title":"Gaussian grouping: Segment and edit anything in 3d scenes","author":"Yu","year":"2024","journal-title":"ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"ref27","article-title":"Learning dynamic convolutions for multi-modal 3d mri brain tumor segmentation","volume-title":"MICCAI Workshop","author":"Yuan","year":"2020"},{"key":"ref28","article-title":"Sam2: Segment anything in images and videos","author":"Gabeur","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-andwhistles","volume-title":"International Conference on Machine Learning","author":"Ryali"},{"key":"ref31","article-title":"Anything3d: Towards single-view anything reconstruction in the wild","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref33","article-title":"Segrefiner: Towards modelagnostic segmentation refinement with discrete diffusion process","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Deep high-resolution representation learning for visual recognition","author":"Sun","year":"2020","journal-title":"TPAMI"},{"key":"ref35","article-title":"Xiv preprint","author":"Wang","year":"2023","journal-title":"Seggpt: Segmenting everything in context."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547"},{"key":"ref37","article-title":"Edit everything: A text-guided generative system for images editing","author":"Xie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Wang","year":"2021","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Embodiedsam: Online segment any 3d thing in real time","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Segment everything everywhere all at once","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2632"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00376"},{"key":"ref44","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"}],"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\/11446039.pdf?arnumber=11446039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:08Z","timestamp":1777529768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02090","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}