{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T03:31:32Z","timestamp":1774063892735,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":"crossref","award":["62376209"],"award-info":[{"award-number":["62376209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["62225208"],"award-info":[{"award-number":["62225208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xtr072024017"],"award-info":[{"award-number":["xtr072024017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcsvt.2024.3504816","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T14:13:26Z","timestamp":1732284806000},"page":"3185-3195","source":"Crossref","is-referenced-by-count":5,"title":["Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3986-5576","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2899-0371","authenticated-orcid":false,"given":"Wei","family":"Ke","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Noah’s Ark Laboratory, Huawei Technologies, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Noah’s Ark Laboratory, Huawei Technologies, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Image and Visual Representation Laboratory, École Polytechnique fédérale de Lausanne, Lausanne, Switzerland"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25874-z"},{"key":"ref5","article-title":"From machine learning to robotics: Challenges and opportunities for embodied intelligence","author":"Roy","year":"2021","journal-title":"arXiv:2110.15245"},{"key":"ref6","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Bucher"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref8","article-title":"Demystifying CLIP data","author":"Xu","year":"2023","journal-title":"arXiv:2309.16671"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref12","article-title":"ZegOT: Zero-shot segmentation through optimal transport of text prompts","author":"Kim","year":"2023","journal-title":"arXiv:2301.12171"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref16","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Li"},{"key":"ref17","article-title":"TagCLIP: Improving discrimination ability of open-vocabulary semantic segmentation","author":"Li","year":"2023","journal-title":"arXiv:2304.07547"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref19","first-page":"4971","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296629"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3361463"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00116"},{"key":"ref27","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref28","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413593"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00942"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00303"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00080"},{"key":"ref35","article-title":"Open-vocabulary universal image segmentation with MaskCLIP","author":"Ding","year":"2022","journal-title":"arXiv:2208.08984"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref37","article-title":"Learning mask-aware CLIP representations for zero-shot segmentation","author":"Jiao","year":"2023","journal-title":"arXiv:2310.00240"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00293"},{"key":"ref39","article-title":"Cross-modal retrieval: A systematic review of methods and future directions","author":"Wang","year":"2023","journal-title":"arXiv:2308.14263"},{"key":"ref40","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref41","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv:2403.05525"},{"key":"ref42","article-title":"Grounding multimodal large language models in actions","author":"Szot","year":"2024","journal-title":"arXiv:2406.07904"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref45","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref46","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","author":"Cheng"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00082"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612133"},{"key":"ref50","article-title":"Cross-modal cognitive consensus guided audio-visual segmentation","author":"Shi","year":"2023","journal-title":"arXiv:2310.06259"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02530"},{"key":"ref52","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref56","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1312.6211"},{"key":"ref57","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00328"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref68","article-title":"In-context prompt learning for test-time vision recognition with frozen vision-language model","author":"Yin","year":"2024","journal-title":"arXiv:2403.06126"},{"key":"ref69","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref70","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109270"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28456"},{"key":"ref75","first-page":"28243","article-title":"Cascade-clip: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref79","volume-title":"MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark","year":"2020"},{"key":"ref80","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292156"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10949577\/10764736.pdf?arnumber=10764736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:54Z","timestamp":1767638454000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10764736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":81,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3504816","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}