{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:39Z","timestamp":1740100959487,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007431","name":"NRF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007431","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892822","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["GViT: Locality enhanced Vision Transformer using Spectral Graph Convolutional Network"],"prefix":"10.1109","author":[{"given":"Longbin","family":"Jin","sequence":"first","affiliation":[{"name":"Konkuk University,Department of Computer Science and Engineering,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eun Yi","family":"Kim","sequence":"additional","affiliation":[{"name":"Konkuk University,Department of Computer Science and Engineering,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2017","journal-title":"ICLRE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"journal-title":"Mobilenets Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref14","article-title":"Localvit: Bringing locality to vision transformers","author":"li","year":"2021","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"journal-title":"GiT Graph interactive transformer for vehicle re-identification","year":"2021","author":"shen","key":"ref16"},{"key":"ref17","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"ICML"},{"key":"ref18","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"journal-title":"Do we really need explicit position encodings for vision transformers?","year":"2021","author":"chu","key":"ref4"},{"key":"ref3","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"2021","journal-title":"NeurIPS"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref7","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref2","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2014","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"ascoli","year":"2021","journal-title":"PMLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref21","article-title":"Early Convolutions Help Transformers See Better","author":"xiao","year":"2021","journal-title":"NeurIPS"},{"journal-title":"GraFormer Graph Convolution Transformer for 3D Pose Estimation","year":"2021","author":"zhao","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892822.pdf?arnumber=9892822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:56:52Z","timestamp":1667516212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892822","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}