{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:18:00Z","timestamp":1777569480255,"version":"3.51.4"},"reference-count":20,"publisher":"IEEE","license":[{"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771303,62071292"],"award-info":[{"award-number":["61771303,62071292"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,5]]},"DOI":"10.1109\/vcip53242.2021.9675337","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":1,"title":["Complex Event Recognition via Spatial-Temporal Relation Graph Reasoning"],"prefix":"10.1109","author":[{"given":"Huan","family":"Lin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongtian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Vivit: A video vision transformer","author":"arnab","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191071"},{"key":"ref15","article-title":"End-to-end video instance segmentation with transformers","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref17","first-page":"10524","article-title":"On layer normalization in the trans-former architecture","author":"xiong","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref5","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref1","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"}],"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\/09675337.pdf?arnumber=9675337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:43:05Z","timestamp":1659483785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9675337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/vcip53242.2021.9675337","relation":{},"subject":[],"published":{"date-parts":[[2021,12,5]]}}}