{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:40:56Z","timestamp":1740102056189,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100008964","name":"Nanjing Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008964","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191965","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["C2SFormer: Rethinking the Local-Global Design for Efficient Visual Recognition Model"],"prefix":"10.1109","author":[{"given":"Yin","family":"Tang","sequence":"first","affiliation":[{"name":"School of Computer Science and Tech., Nanjing Tech University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xili","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Tech., Nanjing Tech University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaping","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Tech., Nanjing Tech University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjie","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Tech., Nanjing Tech University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aichun","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Tech., Nanjing Tech University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"chu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Conditional positional encodings for vision transformers","author":"chu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref32","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref26","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref25","first-page":"20 014","article-title":"Xcit: Cross-covariance image transformers","volume":"34","author":"ali","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref8","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"dai","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"li","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191965.pdf?arnumber=10191965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:46:00Z","timestamp":1692639960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191965","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}