{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T01:41:19Z","timestamp":1725759679717},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897179","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"1551-1555","source":"Crossref","is-referenced-by-count":1,"title":["Conmw Transformer: A General Vision Transformer Backbone With Merged-Window Attention"],"prefix":"10.1109","author":[{"given":"Ang","family":"Li","sequence":"first","affiliation":[{"name":"BUPT,China"}]},{"given":"Jichao","family":"Jiao","sequence":"additional","affiliation":[{"name":"BUPT,China"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"BUPT,China"}]},{"given":"Wangjing","family":"Qi","sequence":"additional","affiliation":[{"name":"BUPT,China"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"The 22nd Research Institute of CETC"}]},{"given":"Min","family":"Pang","sequence":"additional","affiliation":[{"name":"The 22nd Research Institute of CETC"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"aswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"article-title":"Training data-efficient image transformers and distillation through attention","year":"2020","author":"Touvron","key":"ref10"},{"article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","year":"2019","author":"Tan","key":"ref11"},{"article-title":"Transformer in transformer","year":"2021","author":"Han","key":"ref12"},{"article-title":"Do we really need explicit position encodings for vision transformers?","year":"2021","author":"Chu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Twins: Revisiting spatial attention design in vision transformers","year":"2021","author":"Chu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"article-title":"Dual path networks","year":"2017","author":"Chen","key":"ref19"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897179.pdf?arnumber=9897179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:03:40Z","timestamp":1705957420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897179","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}