{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:54Z","timestamp":1740100014385,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413368","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"2455-2459","source":"Crossref","is-referenced-by-count":2,"title":["Human-Aware Coarse-to-Fine Online Action Detection"],"prefix":"10.1109","author":[{"given":"Zichen","family":"Yang","sequence":"first","affiliation":[{"name":"Beihang University,IRIP Lab, School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University,IRIP Lab, School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Qin","sequence":"additional","affiliation":[{"name":"Inception Institute of Artificial Intelligence,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University,IRIP Lab, School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01018"},{"key":"ref3","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351044"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref8","article-title":"Segment-tube: Spatiotemporal action localization in untrimmed videos with per-frame segmentation","author":"le","year":"2018","journal-title":"SENSORS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref2","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ACPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"ref23","article-title":"SGDR: stochastic gradient descent with restarts","author":"loshchilov","year":"2017","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413368.pdf?arnumber=9413368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:04Z","timestamp":1659486004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413368","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}