{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:52Z","timestamp":1777865452490,"version":"3.51.4"},"reference-count":66,"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\/iccv51701.2025.02104","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22664-22675","source":"Crossref","is-referenced-by-count":0,"title":["Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation"],"prefix":"10.1109","author":[{"given":"Yong","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Li","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sule","family":"Bai","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3639996"},{"key":"ref2","article-title":"Univg-r1: Reasoning guided universal visual grounding with reinforcement learning","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"ref4","article-title":"Zero-shot semantic segmentation","author":"Bucher","year":"2019","journal-title":"NeurIPS"},{"key":"ref5","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen","year":"2018","journal-title":"TPAMI"},{"key":"ref7","article-title":"UNITER: learning universal image-text representations","author":"Chen","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1565"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218275"},{"key":"ref15","article-title":"Open-vocabulary image segmentation","author":"Ghiasi","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.233"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32380"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28022"},{"key":"ref23","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref24","first-page":"49044916","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_23"},{"key":"ref27","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref29","first-page":"35313","article-title":"Ordinalclip: Learning rank prompts for language-guided ordinal regression","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"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","article-title":"Qualityaware and selective prior enhancement memory network for video object segmentation","volume-title":"CVPR Workshop","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_37"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_27"},{"key":"ref36","article-title":"Universal segmentation at arbitrary granularity with language instruction","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00335"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3532306"},{"key":"ref39","article-title":"Thinkbot: Embodied instruction following with thought chain reasoning","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref41","article-title":"Soc: Semantic-assisted object cluster for referring video object segmentation","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Hdc: Hierarchical semantic decoding with counting assistance for generalized referring expression segmentation","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719512"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_32"},{"key":"ref46","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref47","article-title":"Hierarchical memory for long video qa","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3514654"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32880"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02694"},{"key":"ref51","article-title":"Hyperseg: Towards universal visual segmentation with large language model","author":"Wei","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","article-title":"Instructseg: Unifying instructed visual segmentation with multi-modal large language models","author":"Wei","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475201"},{"key":"ref54","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00329"},{"key":"ref58","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"NIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref60","article-title":"A simple baseline for zeroshot semantic segmentation with pre-trained vision-language model","author":"Xu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref63","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00689"},{"key":"ref65","article-title":"Flash-vstream: Memorybased real-time understanding for long video streams","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"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\/11444839.pdf?arnumber=11444839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:22Z","timestamp":1777530922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02104","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}