{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T10:55:41Z","timestamp":1784890541917,"version":"3.55.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014881","name":"Guangzhou University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014881","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897881","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"2326-2330","source":"Crossref","is-referenced-by-count":21,"title":["Starvqa: Space-Time Attention for Video Quality Assessment"],"prefix":"10.1109","author":[{"given":"Fengchuang","family":"Xing","sequence":"first","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan-Gen","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangzhou University,School of Computer Science and Cyber Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanpin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leida","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guopu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Tiktok by the numbers"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3470970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_14"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2868063"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01408-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413717"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref14","first-page":"546","article-title":"End-to-end blind quality qssessment of compressed videos using deep neural networks","author":"Liu","year":"2018","journal-title":"ACM-MM"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref16","first-page":"68","article-title":"Stand-alone self-attention in vision models","author":"Ramachandran","year":"2019","journal-title":"NeurIPS"},{"key":"ref17","first-page":"4055","article-title":"Image transformer","author":"Parmar","year":"2018","journal-title":"ICML"},{"key":"ref18","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref20","article-title":"Is space-time attention all you need for video understanding?","author":"Bertasius","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451285"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SSIAI49293.2020.9094606"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref25","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","location":"Bordeaux, France","start":{"date-parts":[[2022,10,16]]},"end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897881.pdf?arnumber=9897881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T20:51:00Z","timestamp":1705956660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897881\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897881","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}