{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:39:00Z","timestamp":1730266740366,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650384","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Feature Enhancement Plugin for Action Recognition"],"prefix":"10.1109","author":[{"given":"Qingmeng","family":"Zhu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanan","family":"He","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukai","family":"Lu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"He","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref5","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Action recognition using visual attention","year":"2015","author":"Sharma","key":"ref8"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"article-title":"Actionclip: A new paradigm for video action recognition","year":"2021","author":"Wang","key":"ref10"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"14","key":"ref13","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proceedings of the fifth Berkeley symposium on mathematical statistics and probability","volume":"1","author":"MacQueen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316801"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/16.1.30"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref17","first-page":"588","article-title":"Beyond hartigan consistency: Merge distortion metric for hierarchical clustering","volume-title":"Conference on Learning Theory","author":"Eldridge"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952118"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380214"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/h0071325"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6247820"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.06.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00777-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108273"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.102678"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","year":"2022","author":"Li","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412502"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"ref35","first-page":"332","article-title":"Movies fight detection dataset","volume-title":"Computer Analysis of Images and Patterns","author":"Nievas","year":"2011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2015.07.514"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1404"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-1115"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.66.2.310"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.372"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650384.pdf?arnumber=10650384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:17:25Z","timestamp":1725945445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650384","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}