{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:39:19Z","timestamp":1751607559217,"version":"3.37.3"},"reference-count":36,"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\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","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\/icassp49357.2023.10096453","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":6,"title":["GSWIN: Gated MLP Vision Model with Hierarchical Structure of Shifted Window"],"prefix":"10.1109","author":[{"given":"Mocho","family":"Go","sequence":"first","affiliation":[{"name":"PKSHA Technology, Inc.,Tokyo,Japan"}]},{"given":"Hideyuki","family":"Tachibana","sequence":"additional","affiliation":[{"name":"PKSHA Technology, Inc.,Tokyo,Japan"}]}],"member":"263","reference":[{"journal-title":"Visual Transformers Token-based Image Representation and Processing for Computer Vision","year":"2020","author":"wu","key":"ref13"},{"key":"ref35","first-page":"6154","article-title":"Cascade R-CNN: Delving into high quality object detection","author":"zhaowei","year":"2018","journal-title":"Proc CVPR"},{"key":"ref12","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc ECCV"},{"key":"ref34","first-page":"2980","article-title":"Mask R-CNN","author":"kaiming","year":"2017","journal-title":"Proc ICCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref14","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"ICML"},{"key":"ref36","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc ECCV"},{"journal-title":"As-mlp An axial shifted mlp architecture for vision","year":"2021","author":"lian","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"journal-title":"Frac-talnet Ultra-deep neural networks without residuals","year":"2016","author":"larsson","key":"ref33"},{"key":"ref10","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"journal-title":"Randaugment Practical automated data augmentation with a reduced search space","year":"2019","author":"cubuk","key":"ref32"},{"key":"ref2","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref1","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref17","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"journal-title":"Localvit Bringing locality to vision transformers","year":"2021","author":"li","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"journal-title":"MetaFormer is Actually What You Need for Vision [J]","year":"2021","author":"yu","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref22","article-title":"Transformer in transformer","volume":"34","author":"han","year":"2021","journal-title":"NeurIPS"},{"journal-title":"Scalable visual transformers with hierarchical pooling","year":"2021","author":"pan","key":"ref21"},{"key":"ref28","article-title":"Vision permutator: A permutable MLP-like architecture for visual recognition","author":"hou","year":"2022","journal-title":"IEEE Trans PAMI"},{"journal-title":"Hire-MLP Vision MLP via hierarchical rearrangement","year":"2021","author":"guo","key":"ref27"},{"journal-title":"CycleMLP A MLP-like architecture for dense prediction","year":"2021","author":"chen","key":"ref29"},{"journal-title":"ResMLP Feedforward Networks for Image Classification with Data-Efficient Training","year":"2021","author":"touvron","key":"ref8"},{"key":"ref7","article-title":"MLP-mixer: An all-mlp architecture for vision","volume":"34","author":"tolstikhin","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","first-page":"9204","article-title":"Pay attention to MLPs","volume":"34","author":"liu","year":"2021","journal-title":"NeurIPS"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"alexey","year":"2021","journal-title":"Proc ICLR"},{"journal-title":"Bert Pre-training of deep bidirectional transformers for language under-standing","year":"2018","author":"devlin","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"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\/10096453.pdf?arnumber=10096453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:05Z","timestamp":1700507165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096453","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}