{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:34:09Z","timestamp":1775579649694,"version":"3.50.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFB1804304"],"award-info":[{"award-number":["2019YFB1804304"]}]},{"DOI":"10.13039\/501100008838","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"publisher","award":["2018-RGZN-02046"],"award-info":[{"award-number":["2018-RGZN-02046"]}],"id":[{"id":"10.13039\/501100008838","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 plan","award":["BP0719010"],"award-info":[{"award-number":["BP0719010"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["18DZ2270700"],"award-info":[{"award-number":["18DZ2270700"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of UHD Video and Audio Production and Presentation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3025665","type":"journal-article","created":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T22:51:34Z","timestamp":1600815094000},"page":"3441-3453","source":"Crossref","is-referenced-by-count":11,"title":["Universal-to-Specific Framework for Complex Action Recognition"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3787-193X","authenticated-orcid":false,"given":"Peisen","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5390-9053","authenticated-orcid":false,"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5165-4325","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2791180"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877936"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2758524"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2786868"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_48"},{"key":"ref27","first-page":"2204","article-title":"Trajectory convolution for action recognition","author":"zhao","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref65","article-title":"Learnable pooling with context gating for video classification","author":"miech","year":"2017","journal-title":"arXiv 1706 06905"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref67","article-title":"Novel dataset for fine-grained image categorization","author":"khosla","year":"0"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref22","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref25","article-title":"Rethinking spatiotemporal feature learning for video understanding","author":"xie","year":"2017","journal-title":"arXiv 1712 04851"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref51","article-title":"Mask-CNN: Localizing parts and selecting descriptors for fine-grained image recognition","author":"wei","year":"2016","journal-title":"arXiv 1605 06878"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.196"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00558"},{"key":"ref57","first-page":"399","article-title":"Videos as space-time region graphs","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","first-page":"2658","article-title":"Actions$\\sim$ transformations","author":"wang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref10","first-page":"695","article-title":"ECO: Efficient convolutional network for online video understanding","author":"zolfaghari","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref12","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922108"},{"key":"ref16","article-title":"Relation attention for temporal action localization","author":"chen","year":"2019","journal-title":"IEEE Trans Multimedia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref5","article-title":"Temporal segment networks for action recognition in videos","author":"wang","year":"2017","journal-title":"arXiv 1705 02953"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"ref7","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2932564"},{"key":"ref48","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref41","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869278"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09204452.pdf?arnumber=9204452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:38Z","timestamp":1652194298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9204452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3025665","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}