{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:48Z","timestamp":1778051508803,"version":"3.51.4"},"reference-count":45,"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\/wacv61042.2026.00600","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6205-6214","source":"Crossref","is-referenced-by-count":0,"title":["Distilling Offline Action Detection Models into Real-Time Streaming Models"],"prefix":"10.1109","author":[{"given":"Deep","family":"Patel","sequence":"first","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasunori","family":"Babazaki","sequence":"additional","affiliation":[{"name":"NEC Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuto","family":"Nagase","sequence":"additional","affiliation":[{"name":"NEC Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iain","family":"Melvin","sequence":"additional","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin Renqiang","family":"Min","sequence":"additional","affiliation":[{"name":"NEC Laboratories America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00804"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref4","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume":"34","author":"Bulat","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00953"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref9","article-title":"Yowov3: An efficient and generalized framework for human action detection and recognition","author":"Nguyen Dang","year":"2024"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00334"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref16","article-title":"Continual transformers: Redundancy-free attention for online inference","author":"Hedegaard","year":"2022"},{"key":"ref17","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0774-7_3"},{"key":"ref19","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00686"},{"key":"ref24","article-title":"You only watch once: A unified cnn architecture for real-time spatiotemporal action localization","author":"K\u00f6p\u00fckl\u00fc","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref26","article-title":"The ava-kinetics localized human actions video dataset","author":"Li","year":"2020"},{"key":"ref27","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00367"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00636"},{"key":"ref36","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref39","article-title":"Distil-xlstm: Learning attention mechanisms through recurrent structures","author":"O Thiombiano","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00035"},{"key":"ref45","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\/11492181.pdf?arnumber=11492181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:14:54Z","timestamp":1778048094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00600","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}