{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:00:57Z","timestamp":1781366457152,"version":"3.54.1"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650303","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":1,"title":["A Complementary Action Recognition Network based on Conv-Transformer"],"prefix":"10.1109","author":[{"given":"Linfu","family":"Liu","sequence":"first","affiliation":[{"name":"Zhengzhou University,School of Electrical and Information Engineering,Zhengzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Qi","sequence":"additional","affiliation":[{"name":"Zhengzhou University,School of Electrical and Information Engineering,Zhengzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Tie","sequence":"additional","affiliation":[{"name":"Zhengzhou University,School of Electrical and Information Engineering,Zhengzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengwu","family":"Liang","sequence":"additional","affiliation":[{"name":"Henan University of Urban Construction,School of Electrical and Control Engineering,Pingdingshan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCCC.2018.8703316"},{"key":"ref2","article-title":"Attention Is All You Need","volume-title":"31st Conference on Neural Information Processing Systems (NIPS 2017)","author":"Vaswani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","author":"Simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref7","author":"Dosovitskiy","year":"2020","journal-title":"An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","first-page":"39653977","article-title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","volume-title":"35th Conference on Neural Information Processing Systems","author":"Dai"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref11","author":"Yan","year":"2021","journal-title":"Contnet: Why Not Use Convolution and Transformer at the Same Time?"},{"key":"ref12","author":"Xiao","year":"2021","journal-title":"Early Convolutions Help Transformers See Better"},{"key":"ref13","author":"Hassani","year":"2021","journal-title":"Escaping the Big Data Paradigm with Compact Transformers"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref17","first-page":"27","article-title":"Two-stream convolutional networks for action recognition in videos[J]","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref25","author":"Dosovitskiy","year":"2020","journal-title":"An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref27","author":"Mohaiminul","year":"2022","journal-title":"Object State Change Classification in Egocentric Videos using the Divided Space-Time Attention Mechanism[J]"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01150"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01185"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref32","author":"Kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref35","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref36","author":"Touvron","year":"2020","journal-title":"Training data-efficient image transformers & distillation through attention"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref41","author":"Zhao","year":"2021","journal-title":"TrTr: Visual tracking with transformer"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"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\/10650303.pdf?arnumber=10650303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:12:42Z","timestamp":1725945162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650303","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}