{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T04:53:33Z","timestamp":1786769613733,"version":"3.56.0"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956379","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1141-1147","source":"Crossref","is-referenced-by-count":34,"title":["Aggregating Global Features into Local Vision Transformer"],"prefix":"10.1109","author":[{"given":"Krushi","family":"Patel","sequence":"first","affiliation":[{"name":"University of Kansas,Department of Electrical Engineering and Computer Science,Lawrence KS,USA,66045"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andres M.","family":"Bur","sequence":"additional","affiliation":[{"name":"University of Kansas,Department of Otolaryngology–Head and Neck Surgery,Kansas City,Kansas,USA,66160"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengjun","family":"Li","sequence":"additional","affiliation":[{"name":"University of Kansas,Department of Electrical Engineering and Computer Science,Lawrence KS,USA,66045"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghui","family":"Wang","sequence":"additional","affiliation":[{"name":"Ryerson University,Department of Computer Science,Toronto ON,Canada,M5B 2K3"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref32","article-title":"Towards more effective prm-based crowd counting via a multi-resolution fusion and attention network","author":"sajid","year":"2021","journal-title":"Neurocomputing"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00254"},{"key":"ref30","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref35","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":"ref34","first-page":"843","article-title":"Revisiting unreasonable effectiveness of data in deep learning era","author":"sun","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CRV52889.2021.00032"},{"key":"ref27","article-title":"Bam: Bottleneck attention module","author":"park","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.12.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref1","first-page":"642","article-title":"Unilmv2: Pseudo-masked language models for unified language model pre-training","author":"bao","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref20","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255809"},{"key":"ref21","article-title":"Fractalnet: Ultra-deep neural networks without residuals","author":"larsson","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref26","article-title":"Miti-detr: Object detection based on transformers with mitigatory self-attention convergence","author":"ma","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108440"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658982"},{"key":"ref11","article-title":"Transformer in transformer","author":"han","year":"2021"},{"key":"ref40","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.126"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref16","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref17","first-page":"4700","article-title":"Densely connected convolutional networks","author":"huang","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref19","article-title":"Cifar-100 (canadian institute for advanced research)","author":"krizhevsky","year":"0"},{"key":"ref4","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","author":"chollet","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"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"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref7","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref46","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"zagoruyko","year":"2016"},{"key":"ref48","article-title":"Nested hierarchical transformer: Towards accurate, data-efficient and-interpretable visual understanding","author":"zhang","year":"2021"},{"key":"ref47","article-title":"Efficient golf ball detection and tracking based on convolutional neural networks and kalman filter","author":"zhang","year":"2020"},{"key":"ref42","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125266"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956379.pdf?arnumber=9956379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:03:44Z","timestamp":1671480224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956379","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}