{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:49:26Z","timestamp":1779202166586,"version":"3.51.4"},"reference-count":73,"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\/iccv51701.2025.02209","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23795-23805","source":"Crossref","is-referenced-by-count":1,"title":["Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction"],"prefix":"10.1109","author":[{"given":"Yunheng","family":"Li","sequence":"first","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan-Sheng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,OpenGVLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nankai University,VCIP, CS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref3","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref6","article-title":"Locality alignment improves vision-language models","author":"Covert","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref8","article-title":"Openvocabulary panoptic segmentation with maskclip","author":"Ding","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Data filtering networks","author":"Fang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4174-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref13","first-page":"1","author":"Gu","year":"2022","journal-title":"Open-vocabulary object detection via vision and language knowledge distillation"},{"key":"ref14","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00360"},{"key":"ref19","first-page":"49044916","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00040-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_23"},{"key":"ref23","first-page":"27896","article-title":"Fineclip: Selfdistilled region-based clip for better fine-grained understanding","volume":"37","author":"Jing","year":"2024","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02319"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","article-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","volume-title":"ICLR","author":"Kuo","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"issue":"4","key":"ref30","first-page":"541","volume":"1","author":"Yann","year":"1989","journal-title":"Backpropagation applied to handwritten zip code recognition. Neural computation"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0430-4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref33","first-page":"28243","article-title":"Cascade-clip: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","volume-title":"ICML","author":"Li","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref35","article-title":"Advancing textual prompt learning with anchored attributes","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref37","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"ICLR","author":"Lin","year":"2032"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref42","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"ICLR","author":"Loshchilov","year":"2017"},{"key":"ref43","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","year":"2019"},{"key":"ref44","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0375-z"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01860"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_3"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref52","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref53","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref57","article-title":"Clipself: Vision transformer distills itself for open-vocabulary dense prediction","volume-title":"ICLR","author":"Wu","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311618"},{"key":"ref64","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01575"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref68","first-page":"36067","article-title":"Glipv2: Unifying localization and vision-language understanding","volume":"35","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref73","article-title":"Mrovseg: Breaking the resolution curse of vision-language models in open-vocabulary semantic segmentation","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11444947.pdf?arnumber=11444947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:45Z","timestamp":1777611705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02209","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}