{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T04:05:02Z","timestamp":1754021102505,"version":"3.37.3"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["81772005"],"award-info":[{"award-number":["81772005"]}],"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":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3258962","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T18:05:13Z","timestamp":1679335513000},"page":"5790-5801","source":"Crossref","is-referenced-by-count":4,"title":["Spatio-Temporal Feature Pyramid Interactive Attention Network for Egocentric Gaze Prediction"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6577-5611","authenticated-orcid":false,"given":"Ming","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TIP.2009.2030969","article-title":"A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression","volume":"19","author":"guo","year":"2010","journal-title":"IEEE Trans Image Process"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","first-page":"1","article-title":"Graph-based visual saliency","volume":"19","author":"harel","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TPAMI.2011.146","article-title":"Image signature: Highlighting sparse salient regions","volume":"34","author":"hou","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162650"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2270394"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_46"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.399"},{"article-title":"A benchmark of computational models of saliency to predict human fixations","year":"2012","author":"judd","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710620"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.86"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2844780"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref47","first-page":"1","article-title":"Predicting human gaze using low-level saliency combined with face detection","volume":"20","author":"cerf","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2799968"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103544"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116894"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.358"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172971"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840724"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2966453"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2905607"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3044440"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/s20185250"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6927"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/s20174960"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635989"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01519-y"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-7-1247-2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.004"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2006.01.013"},{"key":"ref33","article-title":"Simple vs complex temporal recurrences for video saliency prediction","author":"linardos","year":"2019","journal-title":"arXiv 1907 01869"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/34.232073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref76","first-page":"636","article-title":"Computing discrete Fréchet distance","volume":"64","author":"eiter","year":"1994","journal-title":"See Also"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2818151"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2011.04.012"},{"key":"ref39","article-title":"Spatio-temporal self-attention network for video saliency prediction","author":"wang","year":"2021","journal-title":"IEEE Trans Multimedia"},{"key":"ref38","article-title":"Temporal-spatial feature pyramid for video saliency detection","author":"chang","year":"2021","journal-title":"arXiv 2105 04213"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1279920.1279923"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.147"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.648"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2125450"},{"key":"ref68","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Systemss"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164093"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870832"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref64","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref63","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"Predicting video saliency with object-to-motion CNN and two-layer convolutional LSTM","author":"jiang","year":"2017","journal-title":"arXiv 1709 06316"},{"key":"ref66","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947352"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870740"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10076469.pdf?arnumber=10076469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:31:51Z","timestamp":1698085911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10076469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":79,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3258962","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}