{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T13:32:41Z","timestamp":1778160761478,"version":"3.51.4"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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":[[2021,10]]},"DOI":"10.1109\/iccvw54120.2021.00303","type":"proceedings-article","created":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T20:40:09Z","timestamp":1637786409000},"page":"2688-2697","source":"Crossref","is-referenced-by-count":74,"title":["Learning Tracking Representations via Dual-Branch Fully Transformer Networks"],"prefix":"10.1109","author":[{"given":"Fei","family":"Xie","sequence":"first","affiliation":[]},{"given":"Chunyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guangting","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref38","article-title":"Trackingnet: A large-scale dataset and benchmark for object tracking in the wild","author":"muller","year":"2018","journal-title":"ECCV"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"liu","year":"2021"},{"key":"ref32","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref37","article-title":"TrackFormer: Multi-object tracking with transformers","author":"meinhardt","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_43"},{"key":"ref35","article-title":"3S-a discriminative single shot segmentation tracker","author":"lukezic","year":"2020","journal-title":"CVPR"},{"key":"ref34","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_45"},{"key":"ref61","article-title":"Qibin Hou, and Jiashi Feng. Deepvit: Towards deeper vision transformer","author":"zhou","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref2","article-title":"Fully-convolutional siamese networks for object tracking","author":"bertinetto","year":"2016","journal-title":"ECCVW"},{"key":"ref1","year":"0"},{"key":"ref20","article-title":"How to train your energy-based model for regression","author":"gustafsson","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00508"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00508"},{"key":"ref24","article-title":"GOT-10k: A large high-diversity benchmark for generic object tracking in the wild","author":"huang","year":"2019","journal-title":"TPAMI"},{"key":"ref23","article-title":"High-speed tracking with kernelized correlation filters","author":"henriques","year":"2008","journal-title":"ICVS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-68238-5_39","article-title":"The eighth visual object tracking vot2020 challenge results","author":"kristan","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60639-8_26"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref57","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00060","article-title":"Tokens-to-token vit: Training vision transformers from scratch on imagenet","author":"yuan","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"ref55","article-title":"Alpha-refine: Boosting tracking performance by precise bounding box estimation","author":"yan","year":"2020"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.01028","article-title":"Learning spatio-temporal transformer for visual tracking","author":"yan","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref52","article-title":"Learning spatio-appearance memory network for high-performance visual tracking","author":"xie","year":"2020"},{"key":"ref10","article-title":"and Chunhua Shen. Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref17","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00041","article-title":"Crossvit: Cross-attention multi-scale vision transformer for image classification","author":"chen","year":"2021"},{"key":"ref5","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00061","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"wang","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00440"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00632"},{"key":"ref45","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref41","article-title":"Faster R–CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00010","article-title":"Going deeper with image transformers","author":"touvron","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"event":{"name":"2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Montreal, BC, Canada","start":{"date-parts":[[2021,10,11]]},"end":{"date-parts":[[2021,10,17]]}},"container-title":["2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9607382\/9607383\/09607494.pdf?arnumber=9607494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T05:36:59Z","timestamp":1673847419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9607494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccvw54120.2021.00303","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}