{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:18:53Z","timestamp":1776529133026,"version":"3.51.2"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["U23A20286"],"award-info":[{"award-number":["U23A20286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301121"],"award-info":[{"award-number":["62301121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271119"],"award-info":[{"award-number":["62271119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M740529"],"award-info":[{"award-number":["2023M740529"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program (Grade B) of China Postdoctoral Science Foundation","award":["GZB20240120"],"award-info":[{"award-number":["GZB20240120"]}]},{"name":"Independent Research Project of Civil Aviation Flight Technology and Flight Safety Key Laboratory","award":["FZ2022ZZ06"],"award-info":[{"award-number":["FZ2022ZZ06"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3521955","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T14:31:44Z","timestamp":1735050704000},"page":"4144-4157","source":"Crossref","is-referenced-by-count":1,"title":["Cognition Transferring and Decoupling for Text-Supervised Egocentric Semantic Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-8670","authenticated-orcid":false,"given":"Zhaofeng","family":"Shi","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-0311","authenticated-orcid":false,"given":"Heqian","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3745-0262","authenticated-orcid":false,"given":"Lanxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-2567","authenticated-orcid":false,"given":"Fanman","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2936-6340","authenticated-orcid":false,"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7481-095X","authenticated-orcid":false,"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_37"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01440"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2912988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2975845"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057992"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102510"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104335"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00562"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3334526"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106541"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3401451"},{"key":"ref16","article-title":"Ego2Hands: A dataset for egocentric two-hand segmentation and detection","author":"Lin","year":"2020","journal-title":"arXiv:2011.07252"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00812"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00791"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337884"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00106"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3404422"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16338"},{"key":"ref34","first-page":"13745","article-title":"Epic-Kitchens visor benchmark: VIdeo segmentations and object relations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Darkhalil"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref36","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref37","article-title":"CLIP-TD: CLIP targeted distillation for vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2201.05729"},{"key":"ref38","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","author":"Wu","year":"2023","journal-title":"arXiv:2310.01403"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.05.018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3425598"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref48","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Damen"},{"key":"ref49","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018","journal-title":"arXiv:1804.09626"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/computers11020028"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01840"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00543"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"ref56","article-title":"Transformer-based action recognition in hand-object interacting scenarios","author":"Cho","year":"2022","journal-title":"arXiv:2210.11387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00486"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","first-page":"7575","article-title":"Egocentric video-language pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lin"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00481"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00627"},{"key":"ref63","article-title":"Opening the vocabulary of egocentric actions","author":"Chatterjee","year":"2023","journal-title":"arXiv:2308.11488"},{"key":"ref64","article-title":"Eliciting in-context learning in vision-language models for videos through curated data distributional properties","author":"Peter Yu","year":"2023","journal-title":"arXiv:2311.17041"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612484"},{"key":"ref66","article-title":"Towards continual egocentric activity recognition: A multi-modal egocentric activity dataset for continual learning","author":"Xu","year":"2023","journal-title":"arXiv:2301.10931"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01396"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00484"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02194"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.304"},{"key":"ref71","article-title":"Real time egocentric segmentation for video-self avatar in mixed reality","author":"Gonzalez-Sosa","year":"2022","journal-title":"arXiv:2207.01296"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1117\/12.2677242"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"ref77","first-page":"1","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Bucher"},{"key":"ref78","first-page":"10317","article-title":"Consistent structural relation learning for zero-shot segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00692"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6971"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475675"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01293-3"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139459"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01586-9"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00063"},{"key":"ref97","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_26"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00439"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00583"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref104","first-page":"1","article-title":"Efficient inference in fully connected crfs with Gaussian edge potentials","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Kr\u00e4henb\u00fchl"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3236432"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3364764"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3427720"},{"issue":"11","key":"ref111","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10813425.pdf?arnumber=10813425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:38Z","timestamp":1767638498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10813425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":111,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3521955","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}