{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:33Z","timestamp":1774420113673,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889703","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Granularity-Aware Contrastive Learning for Fine-Grained Action Recognition"],"prefix":"10.1109","author":[{"given":"Hailun","family":"Zhang","sequence":"first","affiliation":[{"name":"Sichuan University,College of Computer Science,Chengdu,China"}]},{"given":"Xinrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Sichuan University,College of Computer Science,Chengdu,China"}]},{"given":"Qijun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sichuan University,College of Computer Science,Chengdu,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00137"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref8","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref9","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956311"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31456-9_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref13","article-title":"Layer normalization","volume-title":"NeurIPS","author":"Ba"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref18","first-page":"12 493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref20","first-page":"26 462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Aim: Adapting image models for efficient video action recognition","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yang"},{"key":"ref22","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00289"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889703.pdf?arnumber=10889703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:28Z","timestamp":1774416388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889703","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}