{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:44:39Z","timestamp":1781585079443,"version":"3.54.5"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project","award":["2019YFB1310604"],"award-info":[{"award-number":["2019YFB1310604"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91848108"],"award-info":[{"award-number":["91848108"]}],"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":["62173189"],"award-info":[{"award-number":["62173189"]}],"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":[[2022,12]]},"DOI":"10.1109\/tcsvt.2022.3190314","type":"journal-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T19:38:47Z","timestamp":1657741127000},"page":"8524-8536","source":"Crossref","is-referenced-by-count":31,"title":["Gaze Target Estimation Inspired by Interactive Attention"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-4185","authenticated-orcid":false,"given":"Zhengxi","family":"Hu","sequence":"first","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8901-979X","authenticated-orcid":false,"given":"Kunxu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1746-2693","authenticated-orcid":false,"given":"Hang","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5257-7934","authenticated-orcid":false,"given":"Shichao","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxue","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2645-5655","authenticated-orcid":false,"given":"Jingtai","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref32","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","article-title":"DiverseDepth: Affine-invariant depth prediction using diverse data","author":"yin","year":"2020","journal-title":"arXiv 2002 00569"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref36","first-page":"1","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","author":"wang","year":"0","journal-title":"Proc ICLR"},{"key":"ref35","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref34","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00359"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299110"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940479"},{"key":"ref14","first-page":"35","article-title":"Believe it or not, we know what you are looking at!","author":"lian","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_24"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01263-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01123"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3071621"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref4","author":"recasens","year":"2016","journal-title":"Where are they looking?"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3096333"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341755"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051319"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref5","first-page":"422","article-title":"3D social saliency from head-mounted cameras","volume":"25","author":"park","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/76.465081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3030048"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631185"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0655-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/opmi_a_00049"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref41","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-022-00642-6"},{"key":"ref25","article-title":"Visual-semantic graph attention networks for human-object interaction detection","author":"liang","year":"2020","journal-title":"arXiv 2001 02302"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9973795\/09828503.pdf?arnumber=9828503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:12:28Z","timestamp":1672081948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9828503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3190314","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}