{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T18:17:34Z","timestamp":1759774654445,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447548","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4305-4309","source":"Crossref","is-referenced-by-count":6,"title":["HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition"],"prefix":"10.1109","author":[{"given":"Qian","family":"Wu","sequence":"first","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoxuan","family":"Cui","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029425"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01352"},{"key":"ref7","first-page":"37865","article-title":"Rethinking resolution in the context of efficient video recognition","volume":"35","author":"Ma","year":"2022","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00346"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_42"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00728"},{"article-title":"D-step: Dynamic spatio-temporal pruning","volume-title":"BMVC","author":"Raviv","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00044"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"article-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition","year":"2021","author":"Meng","key":"ref22"},{"article-title":"Adaptive computation time for recurrent neural networks","year":"2016","author":"Graves","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00775"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01508-1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01346"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447548.pdf?arnumber=10447548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:47:40Z","timestamp":1722577660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447548","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}