{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T06:55:44Z","timestamp":1725692144652},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054394","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"2388-2392","source":"Crossref","is-referenced-by-count":2,"title":["Enhanced Action Tubelet Detector for Spatio-Temporal Video Action Detection"],"prefix":"10.1109","author":[{"given":"Yutang","family":"Wu","sequence":"first","affiliation":[]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shuheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qinyu","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"568","article-title":"Twostream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc of NIPS’12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref12","first-page":"6594","article-title":"Modulating early visual processing by language","author":"vries","year":"2017","journal-title":"Proc of NIPS’12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00767-6_28"},{"key":"ref15","first-page":"1","article-title":"Action mach: Maximum average correlation height filter for action recognition","author":"sullivan","year":"2008","journal-title":"Proc CVPR’"},{"key":"ref16","first-page":"2003","article-title":"Discriminative figure-centric models for joint action localization and recognition","author":"lan","year":"2011","journal-title":"Proc ICCV’"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759717"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"journal-title":"Deep learning for detecting multiple space-time action tubes in videos","year":"2016","author":"saha","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref8","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proceedings of ECCV’16"},{"key":"ref7","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref22","first-page":"9935","article-title":"Dance with flow: Two-in-one stream action detection","author":"yu","year":"2019","journal-title":"Proc CVPR’"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00035"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054394.pdf?arnumber=9054394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:28:06Z","timestamp":1656376086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054394","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}