{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:25:54Z","timestamp":1730255154611,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956717","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"3310-3317","source":"Crossref","is-referenced-by-count":2,"title":["TwinLSTM: Two-channel LSTM Network for Online Action Detection"],"prefix":"10.1109","author":[{"given":"Yunfei","family":"Han","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Tan","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref38","first-page":"5532","article-title":"Temporal recurrent networks for on-line action detection","author":"xu","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref32","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"tsochantaridis","year":"2005","journal-title":"In Journal of Machine Learning Research"},{"key":"ref31","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"tran","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref36","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.338"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref18","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref19"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref28"},{"key":"ref4","first-page":"1130","article-title":"Rethinking the faster r-cnn architecture for temporal action localization","author":"chao","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"article-title":"Two-stream convolutional networks for action recognition in videos","year":"2014","author":"simonyan","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","year":"2014","author":"chung","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018118"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"ref1","first-page":"961","article-title":"Activitynet: A large-scale video benchmark for human activity understanding","author":"heilbron","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref22","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00803"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"article-title":"Two-stream convolutional networks for action recognition in videos","year":"2014","author":"simonyan","key":"ref26"},{"key":"ref25","first-page":"4576","article-title":"Joint inference of groups, events and human roles in aerial videos","author":"shu","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956717.pdf?arnumber=9956717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:07:02Z","timestamp":1671480422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956717","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}