{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T12:25:31Z","timestamp":1755692731225},"reference-count":64,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tpami.2020.3029554","type":"journal-article","created":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T19:55:13Z","timestamp":1602100513000},"page":"1-1","source":"Crossref","is-referenced-by-count":16,"title":["Purely Attention Based Local Feature Integration for Video Classification"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Long","sequence":"first","affiliation":[]},{"given":"Gerard","family":"De Melo","sequence":"additional","affiliation":[]},{"given":"Dongliang","family":"He","sequence":"additional","affiliation":[]},{"given":"Fu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhizhen","family":"Chi","sequence":"additional","affiliation":[]},{"given":"Shilei","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref7","first-page":"3476","article-title":"Spatiotemporal residual networks for video action recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Feichtenhofer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref10","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Du"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref14","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12319"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_19"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref24","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985219"},{"key":"ref37","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref38","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2014"},{"key":"ref39","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref40","article-title":"Action recognition using visual attention","author":"Sharma","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref42","article-title":"A deep reinforced model for abstractive summarization","author":"Paulus","year":"2017"},{"key":"ref43","article-title":"A structured self-attentive sentence embedding","author":"Lin","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2576761"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_65"},{"key":"ref47","article-title":"Pyramid attention network for semantic segmentation","author":"Li","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240525"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_23"},{"key":"ref50","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref51","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref53","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref54","first-page":"1","article-title":"The jester dataset: A large-scale video dataset of human gestures,","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. Workshops"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref57","first-page":"26","article-title":"Lecture 6.5-RMSProp: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.09.003"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09216040.pdf?arnumber=9216040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:51:29Z","timestamp":1704844289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3029554","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":[[2020]]}}}