{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:48Z","timestamp":1740169368964,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373300","82150301","62002271","62073218","62133012","62273232","62273231","62003279"],"award-info":[{"award-number":["62373300","82150301","62002271","62073218","62133012","62273232","62273231","62003279"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Key R&D programs of Shaanxi Province","award":["(2021ZDLGY02-06)"],"award-info":[{"award-number":["(2021ZDLGY02-06)"]}]},{"name":"National Defense Science and Technology Key Laboratory Fund Project","award":["6142101210202"],"award-info":[{"award-number":["6142101210202"]}]},{"name":"Qin Chuangyuan Scientist +Engineer","award":["2022KXJ-169"],"award-info":[{"award-number":["2022KXJ-169"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3342076","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T18:52:38Z","timestamp":1702407158000},"page":"141299-141308","source":"Crossref","is-referenced-by-count":1,"title":["Cnnformer: Transformer-Based Semantic Information Enhancement Framework for Behavior Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1245-4336","authenticated-orcid":false,"given":"Jindong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information and Technology, Northwest University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zidong","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Information and Technology, Northwest University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Bai","sequence":"additional","affiliation":[{"name":"Xi’an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1867-7194","authenticated-orcid":false,"given":"Fei","family":"Xie","sequence":"additional","affiliation":[{"name":"Xi’an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Xi’an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information and Technology, Northwest University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5878-1128","authenticated-orcid":false,"given":"Hua","family":"He","sequence":"additional","affiliation":[{"name":"School of Foreign Languages, Northwest University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257546"},{"key":"ref2","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Touvron"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00331"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref6","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst. (NIPS)","author":"Dai"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01957"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref12","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3530989"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3233671"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref28","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","volume":"11929","author":"Dosovitskiy"},{"key":"ref29","first-page":"813","article-title":"Is space-time attention all you need for video understanding","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"2","author":"Bertasius"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_25"},{"key":"ref34","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","volume":"119","author":"Xiong"},{"key":"ref35","first-page":"1","article-title":"Lite transformer with Long-Short Range Attention","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wu"},{"key":"ref36","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"37","author":"Ioffe"},{"key":"ref37","first-page":"1","article-title":"Searching for activation functions","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ramachandran"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref39","first-page":"1","article-title":"Layer normalization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ba"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref42","first-page":"1","article-title":"CT-Net: Channel Tensorization Network for video classification","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10354305.pdf?arnumber=10354305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:03:56Z","timestamp":1705089836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10354305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3342076","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}