{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:20:23Z","timestamp":1761895223068,"version":"build-2065373602"},"reference-count":28,"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"}],"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209160","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":["Perspective Makes Perfect: Prompt-tuning Vision-Language Models for Action Recognition with Diversified Multi-Modal Observation"],"prefix":"10.1109","author":[{"given":"Hailun","family":"Zhang","sequence":"first","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"}]},{"given":"Zhen","family":"Zhai","sequence":"additional","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"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICCV.2011.6126543"},{"year":"2012","author":"Soomro","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","key":"ref2"},{"year":"2023","author":"Zeng","article-title":"Tvtsv2: Learning out-of-the-box spatiotemporal visual representations at scale","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICME55011.2023.00137"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/3560815"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-031-19833-5_7"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TNNLS.2023.3331841"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.11834\/jig.210786"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.11834\/jig.230626"},{"volume-title":"ICLR","author":"Dosovitskiy","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","key":"ref10"},{"volume-title":"ICLR","author":"Jang","article-title":"Categorical reparameterization with gumbel-softmax","key":"ref11"},{"volume-title":"NIPS","author":"Ba","article-title":"Layer normalization","key":"ref12"},{"volume-title":"ICML","author":"Chen","article-title":"A simple framework for contrastive learning of visual representations","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.48550\/arXiv.2102.05095"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV48922.2021.00676"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR52729.2023.00640"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR52688.2022.01569"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR52729.2023.02210"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-031-19833-5_23"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR52729.2023.02206"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR46437.2021.00689"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV48922.2021.00153"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR52688.2022.00289"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/978-3-031-19772-7_1"},{"year":"2017","author":"Kay","article-title":"The kinetics human action video dataset","key":"ref25"},{"year":"2020","author":"Smaira","article-title":"A short note on the kinetics-700-2020 human action dataset","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICCV51070.2023.00371"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1016\/j.patcog.2020.107404"}],"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\/11209160.pdf?arnumber=11209160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:45:58Z","timestamp":1761889558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209160","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}