{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T06:09:20Z","timestamp":1768975760340,"version":"3.49.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673062"],"award-info":[{"award-number":["61673062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2987425","type":"journal-article","created":{"date-parts":[[2020,4,17]],"date-time":"2020-04-17T20:14:42Z","timestamp":1587154482000},"page":"6017-6031","source":"Crossref","is-referenced-by-count":10,"title":["Confidence-Guided Self Refinement for Action Prediction in Untrimmed Videos"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0172-3115","authenticated-orcid":false,"given":"Jingyi","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-6947","authenticated-orcid":false,"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunde","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"3881","article-title":"Improved variational autoencoders for text modeling using dilated convolutions","author":"yang","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref71","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref70","article-title":"ConvNet architecture search for spatiotemporal feature learning","author":"tran","year":"2017","journal-title":"arXiv 1708 05038"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2303090"},{"key":"ref77","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref74","first-page":"1","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.2297321"},{"key":"ref75","author":"ryoo","year":"2010","journal-title":"UT-Interaction Dataset ICPR Contest on Semantic Description of Human Activities (SDHA)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.616"},{"key":"ref78","article-title":"Thumos challenge: Action recognition with a large number of classes","author":"jiang","year":"2014"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00871"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2937757"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00367"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018118"},{"key":"ref37","article-title":"On encoding temporal evolution for real-time action prediction","author":"rezazadegan","year":"2017","journal-title":"arXiv 1709 07894"},{"key":"ref36","first-page":"21","article-title":"Context-aware activity forecasting","author":"chakraborty","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_15"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2898954"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_27"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_33"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00710"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2863279"},{"key":"ref65","first-page":"33","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2771462"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2882805"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396380"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature07200"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2015.04.006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491928"},{"key":"ref23","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"martins","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2751145"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2465-13.2014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/nature09179"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2009.90"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.232"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459278"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.159"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2409553"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818443"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1037\/rev0000045"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797266"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0897-2"},{"key":"ref12","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref82","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc OSDI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref84","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2778559"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01211-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_39"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.290"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.39"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.390"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1126\/science.1185718"},{"key":"ref9","first-page":"7000","article-title":"Action prediction from videos via memorizing hard-to-predict samples","author":"kong","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1037\/xlm0000425"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1037\/xhp0000404"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.obhdp.2006.07.001"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/0956797617744771"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00239"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.173"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1037\/a0022399"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_37"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09070175.pdf?arnumber=9070175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:01Z","timestamp":1651070341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9070175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2987425","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}