{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:56:49Z","timestamp":1771703809562,"version":"3.50.1"},"reference-count":23,"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\/icassp49357.2023.10096602","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":7,"title":["Gaitcotr: Improved Spatial-Temporal Representation for Gait Recognition with a Hybrid Convolution-Transformer Framework"],"prefix":"10.1109","author":[{"given":"Jingqi","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science,Shanghai Key Lab of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science,Shanghai Key Lab of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongming","family":"Shan","sequence":"additional","affiliation":[{"name":"Fudan University,Institute of Science and Technology for Brain-Inspired Intelligence,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science,Shanghai Key Lab of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref12","author":"lee","year":"2021","journal-title":"Vision transformer for small-size datasets"},{"key":"ref23","first-page":"375","article-title":"Gaitedge: Beyond plain end-to-end gait recognition for better practicality","author":"liang","year":"2022","journal-title":"ECCV"},{"key":"ref15","author":"gong","year":"2021","journal-title":"Improve vision transformers training by suppressing over-smoothing"},{"key":"ref14","author":"chu","year":"2021","journal-title":"Conditional positional encodings for vision transformers"},{"key":"ref20","author":"huang","year":"2022","journal-title":"Context-sensitive temporal feature learning for gait recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref22","first-page":"14789","article-title":"Gait recognition in the wild: A benchmark","author":"zhu","year":"2021","journal-title":"ICCV"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02377-4"},{"key":"ref21","first-page":"441","article-title":"A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition","author":"yu","year":"2006","journal-title":"ICPR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01423"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018126"},{"key":"ref17","first-page":"3467","article-title":"GaitSet: Cross-view gait recognition through utilizing gait as a deep set","volume":"44","author":"chao","year":"2022","journal-title":"IEEE Trans PAMI"},{"key":"ref16","article-title":"Anti-oversmoothing in deep vision transformers via the Fourier domain analysis: From theory to practice","author":"wang","year":"2022","journal-title":"ICLRE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2545669"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICB.2016.7550060"},{"key":"ref8","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks","author":"raghu","year":"2021","journal-title":"NeurIPS"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref9","author":"zhang","year":"2022","journal-title":"Spatial transformer network on skeleton-based gait recognition"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01438"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413861"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01267"}],"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\/10096602.pdf?arnumber=10096602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:11Z","timestamp":1700507111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096602","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}