{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:50:14Z","timestamp":1753602614868},"reference-count":26,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096083","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":1,"title":["Look and Think: Intrinsic Unification of Self-Attention and Convolution for Spatial-Channel Specificity"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Gao","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghui","family":"Lin","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiyan","family":"Fang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR46437.2021.01214"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR46437.2021.01625"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV48922.2021.00060"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICCV48922.2021.00061"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref10","article-title":"Standalone self-attention in vision models","author":"ramachandran","year":"2019","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR52688.2022.01186"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref19","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICCV48922.2021.00042"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICCV.2017.322"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref25","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR52688.2022.01167"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICCV.2019.00338"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv 2010 11419"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref5","article-title":"Coatnet: Marrying convolution and attention for all data sizes","author":"dai","year":"2021","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10096083.pdf?arnumber=10096083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:47Z","timestamp":1700506847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096083","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}