{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:32:26Z","timestamp":1761895946035,"version":"build-2065373602"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209787","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition"],"prefix":"10.1109","author":[{"given":"Meng-Zhu","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Union University,Beijing,China"}]},{"given":"Quanxing","family":"Zha","sequence":"additional","affiliation":[{"name":"Huaqiao University,Xiamen,China"}]},{"given":"Hongjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688152"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687719"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"Supmae: Supervised masked autoencoders are efficient vision learners","year":"2022","author":"Liang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347849"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612365"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3436913"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25077"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657806"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687508"},{"article-title":"Prompting visual-language models for dynamic facial expression recognition","year":"2023","author":"Zhao","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"article-title":"A 3 lign-dfer: Pioneering comprehensive dynamic affective alignment for dynamic facial expression recognition with clip","year":"2024","author":"Tao","key":"ref20"},{"key":"ref21","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102382"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00470"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00609"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref27","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","year":"2022","author":"Liang","key":"ref28"},{"article-title":"Token merging: Your vit but faster","year":"2022","author":"Bolya","key":"ref29"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209787.pdf?arnumber=11209787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:02:35Z","timestamp":1761890555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209787","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}