{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:18:24Z","timestamp":1778271504012,"version":"3.51.4"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFB4708200"],"award-info":[{"award-number":["2024YFB4708200"]}]},{"name":"Scientific Research Innovation Capability Support Project for Young Faculty","award":["ZYGXQNJSKYCXNLZCXM-I20"],"award-info":[{"award-number":["ZYGXQNJSKYCXNLZCXM-I20"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24B20173"],"award-info":[{"award-number":["U24B20173"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U2541227"],"award-info":[{"award-number":["U2541227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42327901"],"award-info":[{"award-number":["42327901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Tsinghua University (THU)-Bosch Joint Research Center for Machine Learning","doi-asserted-by":"publisher","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":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3652517","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:02Z","timestamp":1768255442000},"page":"7368-7381","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Vision-Language Model With Fine-Grained Semantics for Open-Vocabulary Segmentation"],"prefix":"10.1109","volume":"36","author":[{"given":"Yong Xien","family":"Chng","sequence":"first","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9191-5588","authenticated-orcid":false,"given":"Xuchong","family":"Qiu","sequence":"additional","affiliation":[{"name":"Bosch Corporate Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5706-8784","authenticated-orcid":false,"given":"Yizeng","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Ding","sequence":"additional","affiliation":[{"name":"Bosch Corporate Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wan","family":"Ding","sequence":"additional","affiliation":[{"name":"Bosch Corporate Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref7","article-title":"Natural language for human\u2013robot collaboration: Problems beyond language grounding","author":"Pate","year":"2021","journal-title":"arXiv:2110.04441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852786"},{"key":"ref9","first-page":"8090","article-title":"Open-vocabulary universal image segmentation with MaskCLIP","volume-title":"Proc. ICML","author":"Ding"},{"key":"ref10","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional CLIP","volume-title":"Proc. NeurIPS","author":"Yu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_23"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref14","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3464631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454227"},{"key":"ref18","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441036"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3435710"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3393632"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370570"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375306"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292156"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3293166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285091"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3515088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3509504"},{"key":"ref30","article-title":"Language-driven semantic segmentation","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3484490"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01397"},{"key":"ref44","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref49","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3102509"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042065"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3526054"},{"key":"ref54","article-title":"Tuning LayerNorm in attention: Towards efficient multi-modal LLM finetuning","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref55","first-page":"11285","article-title":"TinyTL: Reduce activations, not trainable parameters for efficient on-device learning","volume-title":"Proc. NeurIPS","author":"Cai"},{"key":"ref56","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NACL: HLT","author":"Devlin"},{"issue":"70","key":"ref57","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref58","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref59","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref60","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref61","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. ICLR","author":"Su"},{"key":"ref62","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref63","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref64","article-title":"Masked vision and language modeling for multi-modal representation learning","volume-title":"Proc. ICLR","author":"Kwon"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3546312"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681061"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref71","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11342322.pdf?arnumber=11342322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:21Z","timestamp":1778269341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":77,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3652517","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}