{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:48:34Z","timestamp":1778860114106,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097256","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["DMFormer: Closing the gap Between CNN and Vision Transformers"],"prefix":"10.1109","author":[{"given":"Zimian","family":"Wei","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengyue","family":"Pan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lujun","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Menglong","family":"Lu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Niu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peijie","family":"Dong","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref24","article-title":"Visual attention network","author":"guo","year":"2022"},{"key":"ref12","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref14","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021"},{"key":"ref20","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"chu","year":"2021"},{"key":"ref11","article-title":"Mixconv: Mixed depthwise convolutional kernels","author":"tan","year":"2019"},{"key":"ref22","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018"},{"key":"ref10","article-title":"Pvtv2: Improved baselines with pyramid vision transformer","author":"wang","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref2","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref8","article-title":"On the connection between local attention and dynamic depth-wise convolution","author":"han","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref7","first-page":"11963","article-title":"Scaling up your kernels to 31x31: Revisiting large kernel design in cnns","author":"ding","year":"2022","journal-title":"CVPR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref4","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"huang","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097256.pdf?arnumber=10097256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:02:10Z","timestamp":1699902130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097256","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}