{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:58:20Z","timestamp":1789347500682,"version":"build-2803163510"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61831015"],"award-info":[{"award-number":["61831015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62176159"],"award-info":[{"award-number":["62176159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62301316"],"award-info":[{"award-number":["62301316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2021YFE0206700"],"award-info":[{"award-number":["2021YFE0206700"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["21ZR1432200"],"award-info":[{"award-number":["21ZR1432200"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100002858","name":"China Post-Doctoral Science Foundation","doi-asserted-by":"publisher","award":["2023TQ0212"],"award-info":[{"award-number":["2023TQ0212"]}],"id":[{"id":"10.13039\/501100002858","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":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3318839","type":"journal-article","created":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:40:20Z","timestamp":1695667220000},"page":"3271-3285","source":"Crossref","is-referenced-by-count":12,"title":["Un-Gaze: A Unified Transformer for Joint Gaze-Location and Gaze-Object Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9632-9131","authenticated-orcid":false,"given":"Danyang","family":"Tu","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1235-598X","authenticated-orcid":false,"given":"Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3071621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00544"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3061719"},{"key":"ref8","first-page":"84","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547955"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00676"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01123"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3225865"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_41"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","volume-title":"Eye Tracking: A Comprehensive Guide to Methods Measures","author":"Holmqvist","year":"2011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3190314"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900709"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20053"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.188"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref27","first-page":"103","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2844780"},{"key":"ref30","first-page":"42","article-title":"Where are they looking?","volume-title":"Proc. NIPS","author":"Recasens"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref32","first-page":"22","article-title":"Action is in the eye of the beholder: Eye-gaze driven model for spatio-temporal action localization","volume-title":"Proc. NIPS","author":"Shapovalova"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093515"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00386"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00349"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_6"},{"key":"ref39","first-page":"127","article-title":"Video-based human-object interaction detection from tubelet tokens","volume-title":"Proc. NIPS","author":"Tu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","article-title":"FCHD: Fast and accurate head detection in crowded scenes","author":"Vora","year":"2018","journal-title":"arXiv:1809.08766"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01898"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.153"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/689"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299081"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01263-4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2909982"},{"key":"ref50","first-page":"1","article-title":"WHENet: Real-time fine-grained estimation for wide range head pose","volume-title":"Proc. BMVC","author":"Zhou"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.341"},{"key":"ref52","first-page":"788","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.148"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10262016.pdf?arnumber=10262016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:11:32Z","timestamp":1736453492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10262016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":53,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3318839","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}