{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:06:55Z","timestamp":1783202815202,"version":"3.54.6"},"reference-count":52,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160400"],"award-info":[{"award-number":["2022ZD0160400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271346,62206031,U21B2037"],"award-info":[{"award-number":["62271346,62206031,U21B2037"]}],"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\/iccv51701.2025.02154","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23199-23209","source":"Crossref","is-referenced-by-count":2,"title":["CLIPeR: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Lin","family":"Sun","sequence":"first","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiale","family":"Cao","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"Chongqing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhengzhou University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref2","first-page":"468","article-title":"Zero-shot semantic segmentation","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00394"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref10","first-page":"8090","article-title":"Openvocabulary panoptic segmentation with maskclip","volume-title":"International Conference on Machine Learning","author":"Ding"},{"key":"ref11","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref13","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00406"},{"key":"ref18","first-page":"28243","article-title":"Cascade-clip: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28139"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref24","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"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref28","article-title":"ViewCo: Discovering text-supervised segmentation masks via multi-view semantic consistency","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387326"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3681368"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01251"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521825"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"ref39","article-title":"Diffusion model is secretly a training-free open vocabulary semantic segmenter","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128437"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"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"}],"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\/11444085.pdf?arnumber=11444085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:46:06Z","timestamp":1777610766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02154","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}