{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:13Z","timestamp":1777888753484,"version":"3.51.4"},"reference-count":68,"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 Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62425114,62121002,U23B2028,62232006"],"award-info":[{"award-number":["62425114,62121002,U23B2028,62232006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009076","name":"USTC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","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\/iccv51701.2025.02228","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24034-24044","source":"Crossref","is-referenced-by-count":0,"title":["CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Jiannan","family":"Ge","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pandeng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun-Ao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00149"},{"key":"ref3","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00132"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"ref9","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02262"},{"key":"ref11","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"issue":"70","key":"ref13","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"issue":"1\u201345","key":"ref16","first-page":"5","article-title":"The pascal visual object classes challenge 2012 (voc2012) development kit","volume":"2007","author":"Everingham","year":"2012","journal-title":"Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","author":"Honnibal","year":"2020","journal-title":"spaCy: Industrial-strength Natural Language Processing in Python"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref25","article-title":"Diffusion models for zero-shot open-vocabulary segmentation","author":"Karazija","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3418210"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref29","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","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":"ref31","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref34","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01633"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"ref38","first-page":"23033","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"International Conference on Machine Learning","author":"Luo","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"issue":"Part V 16","key":"ref40","first-page":"647","article-title":"Connecting vision and language with localized narratives","volume-title":"Computer Vision-ECCV 2020: 16th European Conference","author":"Jordi","year":"2020"},{"key":"ref41","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":"ref42","first-page":"1162","article-title":"Zeroguidance segmentation using zero segment labels","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Rewatbowornwong","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02684"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref45","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Self-guided open-vocabulary semantic segmentation","author":"Osman","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"Amber: An 11 m -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00329"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3011"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref57","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref59","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","article-title":"Next-chat: An 1 mm for chat, detection and segmentation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3222"},{"key":"ref62","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00262"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref66","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28614"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680885"}],"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\/11444948.pdf?arnumber=11444948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:41Z","timestamp":1777611281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02228","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}