{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:56Z","timestamp":1777865336565,"version":"3.51.4"},"reference-count":53,"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":["QTZX23042"],"award-info":[{"award-number":["QTZX23042"]}],"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\/iccv51701.2025.02116","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22794-22803","source":"Crossref","is-referenced-by-count":0,"title":["\ud835\udc9f\u2110\u210b-CLIP: Unleashing the Diversity of Multi-Head Self-Attention for Training-Free Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Songsong","family":"Duan","sequence":"first","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University,State Key Laboratory of Integrated Services Networks,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University,State Key Laboratory of Integrated Services Networks,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University,State Key Laboratory of Integrated Services Networks,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00354"},{"key":"ref3","article-title":"Talking to dino: Bridging selfsupervised vision backbones with language for open-vocabulary segmentation","author":"Barsellotti","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref10","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume-title":"NeurIPS","author":"Cheng"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","article-title":"Freeseg-diff: Training-free open-vocabulary segmentation with diffusion models","author":"Toniella Corradini","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00495"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"ref20","article-title":"Class distribution-induced attention map for open-vocabulary semantic segmentations","volume-title":"ICLR","author":"Un Kang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume-title":"NeurIPS","author":"Kr\u00e4henb\u00fchl"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref29","first-page":"103031","article-title":"Vmamba: Visual state space model","volume-title":"NeurIPS","author":"Liu"},{"key":"ref30","first-page":"23033","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"ICML","author":"Luo"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00386"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01408"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_9"},{"key":"ref37","first-page":"33754","article-title":"Reco: Retrieve and co-segment for zero-shot transfer","volume-title":"NeurIPS","author":"Shin"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_20"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3461954"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00176"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00094"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref46","first-page":"26794","article-title":"Image-text codecomposition for text-supervised semantic segmentation","volume-title":"CVPR","author":"Wu"},{"key":"ref47","article-title":"Clipself: Vision transformer distills itself for open-vocabulary dense prediction","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01919-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"}],"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\/11445045.pdf?arnumber=11445045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:16Z","timestamp":1777529836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02116","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}