{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:08Z","timestamp":1777890248696,"version":"3.51.4"},"reference-count":60,"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":["62106149"],"award-info":[{"award-number":["62106149"]}],"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\/iccv51701.2025.01977","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21288-21298","source":"Crossref","is-referenced-by-count":0,"title":["Text-Guided Visual Prompt DINO for Generic Segmentation"],"prefix":"10.1109","author":[{"given":"Yuchen","family":"Guan","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent Inc.,WeChat AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Canmiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent Inc.,WeChat AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Inc.,WeChat AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc.,WeChat AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Chen","year":"2023","journal-title":"Position-enhanced visual instruction tuning for multimodal large language models"},{"key":"ref2","author":"Chen","year":"2023","journal-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref5","author":"Cheng","year":"2025","journal-title":"Whoever started the interference should end it: Guiding data-free model merging via task vectors"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref9","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref11","author":"Gu","year":"2021","journal-title":"Open-vocabulary object detection via vision and language knowledge distillation"},{"key":"ref12","volume-title":"Enhancing logits distillation with plug&play kendall\u2019s \u03c4 ranking loss","author":"Guan","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref14","volume-title":"spacy: Industrial-strength natural language processing in python","author":"Honnibal","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref16","first-page":"38","article-title":"T-rex2: Towards generic object detection via text-visual prompt synergy","volume-title":"European Conference on Computer Vision","author":"Jiang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01222"},{"key":"ref23","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref31","author":"van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_19"},{"key":"ref33","author":"Peng","year":"2023","journal-title":"Kosmos-2: Grounding multimodal large language models to the world"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref36","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref42","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01704"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01732"},{"key":"ref45","author":"Wei","year":"2025","journal-title":"Unifying multimodal large language model capabilities and modalities via model merging"},{"key":"ref46","article-title":"Open-vocabulary customization from clip via data-free knowledge distillation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wei","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"ref48","author":"Yang","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref52","author":"Zhang","year":"2022","journal-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref57","author":"Zhu","year":"2020","journal-title":"Deformable detr: Deformable transformers for end-to-end object detection"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"}],"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\/11445653.pdf?arnumber=11445653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:28Z","timestamp":1777613548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01977","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}