{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:21Z","timestamp":1777890201726,"version":"3.51.4"},"reference-count":77,"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\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2106825"],"award-info":[{"award-number":["2106825"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.02029","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21853-21863","source":"Crossref","is-referenced-by-count":0,"title":["Refer to Any Segmentation Mask Group with Vision-Language Prompts"],"prefix":"10.1109","author":[{"given":"Shengcao","family":"Cao","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijun","family":"Wei","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Kuen","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangning","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiuxiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"HyunJoon","family":"Jung","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Yan","family":"Gui","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Xiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Adobe Inc","year":"2023","journal-title":"Photoshop: Generative Fill"},{"key":"ref2","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"In ECCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref4","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref7","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"In NACCL"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"In ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3408255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"In ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref25","article-title":"VR-GPT: Visual language model for intelligent virtual reality applications","author":"Konenkov","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref28","article-title":"CoVLM: Composing visual entities and relationships in large language models via communicative decoding","author":"Li","year":"2024","journal-title":"In ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711845"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref39","article-title":"HDC: Hierarchical semantic decoding with counting assistance for generalized referring expression segmentation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref41","article-title":"Visual instruction inversion: Image editing via image prompting","author":"Nguyen","year":"2023","journal-title":"In NeurIPS"},{"key":"ref42","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"TMLR"},{"key":"ref43","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2024","journal-title":"In ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3227513"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00374"},{"key":"ref47","article-title":"Improving language understanding by generative pre-training","author":"Radford","journal-title":"2018"},{"key":"ref48","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"In ICML"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.561"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref53","article-title":"Empowering visual creativity: A visionlanguage assistant to image editing recommendations","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref56","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs","author":"Tong","year":"2024","journal-title":"In NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref58","author":"Touvron","year":"2023","journal-title":"LLaMA: Open and efficient foundation language models"},{"key":"ref59","article-title":"Pointer networks","author":"Vinyals","year":"2015","journal-title":"In NeurIPS"},{"key":"ref60","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023","journal-title":"In NeurIPS"},{"key":"ref61","article-title":"CRIS: CLIPdriven referring image segmentation","author":"Wang","year":"2022","journal-title":"In CVPR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240541"},{"key":"ref64","article-title":"A survey on robotics with foundation models: toward embodied AI","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_21"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref75","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024","journal-title":"In ICLR"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref77","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2024","journal-title":"In NeurIPS"}],"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\/11445121.pdf?arnumber=11445121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:28Z","timestamp":1777613488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02029","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}