{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:28:47Z","timestamp":1760956127077},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506453","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T21:08:41Z","timestamp":1629752921000},"page":"1089-1093","source":"Crossref","is-referenced-by-count":8,"title":["Two-Pathway Transformer Network for Video Action Recognition"],"prefix":"10.1109","author":[{"given":"Bo","family":"Jiang","sequence":"first","affiliation":[{"name":"AI Business Unit, NetEase Inc.,Ambilight Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahong","family":"Yu","sequence":"additional","affiliation":[{"name":"AI Business Unit, NetEase Inc.,Ambilight Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhou","sequence":"additional","affiliation":[{"name":"AI Business Unit, NetEase Inc.,Ambilight Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kailin","family":"Wu","sequence":"additional","affiliation":[{"name":"AI Business Unit, NetEase Inc.,Ambilight Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"AI Business Unit, NetEase Inc.,Ambilight Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"363","article-title":"Hidden two-stream convolutional networks for action recognition","author":"zhu","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref11","first-page":"5533","article-title":"Learning spatio-temporal representation with pseudo-3d residual networks","author":"qiu","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref15","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"christoph","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Lightweight network architecture for real-time action recognition","author":"kozlov","year":"2019","journal-title":"arXiv preprint arXiv 1905 09010"},{"key":"ref19","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv preprint arXiv 1212 0402"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref6","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":"ref5","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":"ref8","article-title":"Slowfast networks for video recognition","author":"feichtenhofer","year":"2018","journal-title":"arXiv preprint arXiv 1812 07636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref9","article-title":"Temporal shift module for efficient video understanding","author":"lin","year":"2018","journal-title":"arXiv preprint arXiv 1811 08383"},{"key":"ref1","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"European Conference on Computer Vision"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2021,9,19]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506453.pdf?arnumber=9506453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T23:57:56Z","timestamp":1670371076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506453","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}