{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:16:26Z","timestamp":1780395386919,"version":"3.54.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00038","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"308-317","source":"Crossref","is-referenced-by-count":1,"title":["ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes"],"prefix":"10.1109","author":[{"given":"Jiaojiao","family":"Zhao","sequence":"first","affiliation":[{"name":"Prime Video at Amazon"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539875"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00334"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","article-title":"Neural bipartite matching","author":"Georgiev","year":"2020"},{"key":"ref10","article-title":"A better baseline for ava","author":"Girdhar","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01739"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref21","article-title":"You only watch once: A unified cnn architecture for real-time spatiotemporal action localization","author":"K\u00f6p\u00fckl\u00fc","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_30"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01328"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref28","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref32","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"ICML","author":"Ryali"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.58"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"ICLR","author":"Simonyan"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.393"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00595"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref38","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref41","article-title":"Max-margin structured output regression for spatio-temporal action localization","volume-title":"NeurIPS","author":"Tran"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref43","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00035"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492604.pdf?arnumber=11492604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:45:03Z","timestamp":1778049903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00038","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}