{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:00:06Z","timestamp":1771700406471,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 109-2622-E-194-004,MOST 109-2622-E-194-003"],"award-info":[{"award-number":["MOST 109-2622-E-194-004,MOST 109-2622-E-194-003"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,5]]},"DOI":"10.1109\/vcip53242.2021.9675340","type":"proceedings-article","created":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T20:37:19Z","timestamp":1642624639000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Action Recognition Improved by Correlations and Attention of Subjects and Scene"],"prefix":"10.1109","author":[{"given":"Manh-Hung","family":"Ha","sequence":"first","affiliation":[]},{"given":"Oscal Tzyh-Chiang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","author":"bochkovskiy","year":"2020","journal-title":"Darknet Open source neural networks in python"},{"key":"ref11","first-page":"7922","article-title":"Pa3d: Pose-action 3d machine for video recognition","author":"li","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref12","first-page":"3725","article-title":"Rpan: An end-to-end recurrent pose-attention network for action recognition in videos","author":"wang","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref13","first-page":"1833","article-title":"Traffic police gesture recognition by pose graph convolutional networks","author":"guo","year":"0","journal-title":"Proc of IEEE Intelligent Vehicles Symposium"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.103"},{"key":"ref15","article-title":"Generating long sequences with sparse transformers","author":"radford","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"han","year":"0","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref18","article-title":"An end-to-end 3D convolutional neural network for action detection and segmentation in videos","author":"chen","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"7794","article-title":"Non-local neural networks","author":"gupta","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","first-page":"7024","article-title":"Potion: Pose motion representation for action recognition","author":"revaud","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref6","first-page":"318","article-title":"Actor-centric relation network","author":"vondrick","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"parmar","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"kolesnikov","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"3588","article-title":"Relation networks for object detection","author":"zhang","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048741"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"}],"event":{"name":"2021 International Conference on Visual Communications and Image Processing (VCIP)","location":"Munich, Germany","start":{"date-parts":[[2021,12,5]]},"end":{"date-parts":[[2021,12,8]]}},"container-title":["2021 International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9675283\/9675313\/09675340.pdf?arnumber=9675340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:57:34Z","timestamp":1652201854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9675340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/vcip53242.2021.9675340","relation":{},"subject":[],"published":{"date-parts":[[2021,12,5]]}}}