{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:16:13Z","timestamp":1768342573813,"version":"3.49.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":["61972012"],"award-info":[{"award-number":["61972012"]}],"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":["61732016"],"award-info":[{"award-number":["61732016"]}],"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":["61906064"],"award-info":[{"award-number":["61906064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2020.3030048","type":"journal-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T20:20:34Z","timestamp":1602534034000},"page":"6631-6646","source":"Crossref","is-referenced-by-count":23,"title":["First- And Third-Person Video Co-Analysis By Learning Spatial-Temporal Joint Attention"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7983-6465","authenticated-orcid":false,"given":"Huangyue","family":"Yu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6688-3710","authenticated-orcid":false,"given":"Minjie","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6898-0058","authenticated-orcid":false,"given":"Yunfei","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9064-7964","authenticated-orcid":false,"given":"Feng","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6636"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2313123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00046"},{"key":"ref59","first-page":"1","article-title":"Object cosegmentation using deep siamese network","author":"mukherjee","year":"2018","journal-title":"Proc Int Conf Pattern Recognit Artif Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00055"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.81"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2982828"},{"key":"ref52","first-page":"435","article-title":"Semantic aware attention based deep object co-segmentation","author":"chen","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref11","first-page":"639","article-title":"In the eye of beholder: Joint learning of gaze and actions in first person video","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2657880"},{"key":"ref10","first-page":"1","article-title":"Summarizing first-person videos from third persons’ points of views","author":"ho","year":"2017","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00129"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00243"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_32"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.160"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00941"},{"key":"ref45","first-page":"9890","article-title":"You2Me : Inferring body pose in egocentric video via first and second person interactions by evonne","author":"ng","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","first-page":"1","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2921539"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803534"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00151"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01440"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299183"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350896"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2799847"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240536"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00369"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref33","first-page":"1","article-title":"Localizing and orienting street views using overhead imagery","author":"vo","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00758"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2806381"},{"key":"ref39","first-page":"1","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref68","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"sigurdsson","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A model of saliency-based visual attention for rapid scene analysis","volume":"20","author":"itti","year":"1998","journal-title":"IEEE Trans Pattern Anal and Mach Intell"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2018.8466472"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref64","first-page":"505","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00061"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"altman","year":"1992","journal-title":"Amer Statist"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12334"},{"key":"ref65","first-page":"1","article-title":"Video summarization with long short-term memory","author":"zhang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref29","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123393"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123297"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09220850.pdf?arnumber=9220850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T20:56:16Z","timestamp":1723755376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9220850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":69,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3030048","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}