{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:23:27Z","timestamp":1740101007603,"version":"3.37.3"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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","award":["61972417,61902431"],"award-info":[{"award-number":["61972417,61902431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2020MF005"],"award-info":[{"award-number":["ZR2020MF005"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892630","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Pcwin Transformer: Permuted Channel Window based Attention for Image Classification"],"prefix":"10.1109","author":[{"given":"Shibao","family":"Li","sequence":"first","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuerong","family":"Cui","sequence":"additional","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunwu","family":"Zhang","sequence":"additional","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zekun","family":"Jia","sequence":"additional","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinze","family":"Zhu","sequence":"additional","affiliation":[{"name":"China University of Petroleum,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Toward transformer-based object detection","volume":"abs 2012 9958","author":"beal","year":"2020","journal-title":"ArXiv"},{"journal-title":"pytorch-image-models","year":"2019","author":"wightman","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00314"},{"key":"ref31","article-title":"Convit: Improving vision transformers with soft convolutional inductive biases","author":"d'ascoli","year":"0","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref34","article-title":"Resnest: Split-attention networks","volume":"abs 2004 8955","author":"zhang","year":"2020","journal-title":"ArXiv"},{"key":"ref10","article-title":"Epsanet: An efficient pyramid split attention block on convolutional neural network","volume":"abs 2105 14447","author":"zhang","year":"2021","journal-title":"ArXiv"},{"key":"ref40","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"abs 2101 3961","author":"fedus","year":"2021","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Wide residual networks","volume":"abs 1605 7146","author":"zagoruyko","year":"2016","journal-title":"ArXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref17","article-title":"Image transformer","volume":"abs 1802 5751","author":"parmar","year":"2018","journal-title":"ArXiv"},{"key":"ref18","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"0","journal-title":"ICML"},{"key":"ref19","article-title":"Deep-vit: Towards deeper vision transformer","volume":"abs 2103 11886","author":"zhou","year":"2021","journal-title":"ArXiv"},{"key":"ref28","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2019","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref27","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume":"abs 1905 11946","author":"tan","year":"2019","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","article-title":"Generative pretraining from pixels","author":"chen","year":"0","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"0","journal-title":"NeurIPS 2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"ICLRE"},{"key":"ref9","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"0","journal-title":"ECCV"},{"key":"ref1","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Computer Vision - ECCV 2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref22","article-title":"Attention is all you need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"ArXiv"},{"key":"ref21","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"0","journal-title":"NeurIPS"},{"key":"ref42","article-title":"Longformer: The long-document transformer","volume":"abs 2004 5150","author":"beltagy","year":"2020","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref41","article-title":"Reformer: The efficient transformer","volume":"abs 2001 4451","author":"kitaev","year":"2020","journal-title":"ArXiv"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2015","journal-title":"CoRR"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref26","first-page":"1","article-title":"Deep high-resolution representation learning for visual recognition","volume":"pp","author":"wang","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Computer Vision - ECCV 2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892630.pdf?arnumber=9892630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:59:45Z","timestamp":1667516385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892630","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}