{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:54:45Z","timestamp":1781196885135,"version":"3.54.1"},"reference-count":28,"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\/icassp48485.2024.10446442","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3200-3204","source":"Crossref","is-referenced-by-count":3,"title":["Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval"],"prefix":"10.1109","author":[{"given":"Rui","family":"Deng","sequence":"first","affiliation":[{"name":"NetEase Yidun AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Wu","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Fu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref2","article-title":"Adafocus+: Adaptive focus for efficient video recognition","volume-title":"ICCV","author":"Zhang"},{"key":"ref3","article-title":"Oc-sampler: Compressing videos to one clip with single-step sampling","volume-title":"CVPR","author":"Cai"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_42"},{"key":"ref5","author":"Raviv","year":"2022","journal-title":"D-step: Dynamic spatio-temporal pruning"},{"key":"ref6","article-title":"Liteeval: A coarse-to-fine framework for resource efficient video recognition","volume-title":"NIPS","author":"Liu"},{"key":"ref7","article-title":"Ar-net: Adaptive frame resolution for efficient action recognition","volume-title":"ECCV","author":"Yang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref12","article-title":"Mvit: Multiscale vision transformers for large-scale remote sensing image classification","volume-title":"CVPR","author":"Liu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","author":"Rao","year":"2000","journal-title":"Reinforcement learning: An introduction"},{"key":"ref15","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"CVPR","author":"Dosovitskiy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00331"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00645"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222915"},{"key":"ref21","first-page":"9508","article-title":"Learning with differentiable pertubed optimizers","volume":"33","author":"Berthet","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2905741"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.49"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28046"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2713410"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3165177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10446442.pdf?arnumber=10446442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:16:46Z","timestamp":1722575806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446442","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}