{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:37:31Z","timestamp":1780519051543,"version":"3.54.1"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018AAA0102802"],"award-info":[{"award-number":["2018AAA0102802"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62036011"],"award-info":[{"award-number":["62036011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Research Program of Frontier Sciences, CAS","award":["QYZDJ-SSW-JSC040"],"award-info":[{"award-number":["QYZDJ-SSW-JSC040"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tpami.2021.3100277","type":"journal-article","created":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T20:48:15Z","timestamp":1627418895000},"page":"7010-7028","source":"Crossref","is-referenced-by-count":10,"title":["Interaction-Aware Spatio-Temporal Pyramid Attention Networks for Action Classification"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9237-8825","authenticated-orcid":false,"given":"Weiming","family":"Hu","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0439-2692","authenticated-orcid":false,"given":"Haowei","family":"Liu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Du","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-4961","authenticated-orcid":false,"given":"Chunfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5888-6735","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2113-9119","authenticated-orcid":false,"given":"Stephen","family":"Maybank","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Systems, Birkbeck College, University of London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref2","article-title":"TRECVID 2016: Evaluating video search, video event detection, localization, and hyperlinking","author":"Awad","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref6","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-038"},{"key":"ref9","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref12","first-page":"1","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref13","article-title":"Action recognition using visual attention","author":"Sharma","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11744047_33"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88688-4_48"},{"key":"ref26","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref29","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feichtenhofer"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref41","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref42","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref46","first-page":"34","article-title":"Attentional pooling for action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Girdhar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1261097"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00103"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00185"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_50"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.83"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018247"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2174\/1874479611104030147"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985219"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093283"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00958"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref75","first-page":"1","article-title":"Dynamic graph modules for modeling object-object interactions in activity recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Huang"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01211-2"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6983"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978613"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107037"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054200"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01017"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00094"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00240"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076522"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref94","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9893033\/09497754.pdf?arnumber=9497754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:12:55Z","timestamp":1705018375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9497754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":93,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3100277","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":[[2022,10,1]]}}}