{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:40Z","timestamp":1766061700489,"version":"3.48.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247730","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20677-20684","source":"Crossref","is-referenced-by-count":0,"title":["Efficient and Accurate Low-Resolution Transformer Tracking"],"prefix":"10.1109","author":[{"given":"Shaohua","family":"Dong","sequence":"first","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhe","family":"Feng","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Liang","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Yang","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuewei","family":"Lin","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Fan","sequence":"additional","affiliation":[{"name":"University of North Texas,Dept. of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref2","article-title":"Swintrack: A simple and strong baseline for transformer tracking","author":"Lin","year":"2022","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00881"},{"key":"ref8","article-title":"Mixformerv2: Efficient fully transformer tracking","author":"Cui","year":"2023","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00162"},{"article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International Conference on Machine Learning (ICML)","author":"Tan","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.518"},{"key":"ref13","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","author":"Wang","year":"2021","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref16","article-title":"Zoomtrack: Target-aware non-uniform resizing for efficient visual tracking","author":"Kou","year":"2023","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_37"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"ref31","article-title":"Learning efficient object detection models with knowledge distillation","author":"Chen","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref32","article-title":"Rethinking resolution in the context of efficient video recognition","author":"Ma","year":"2022","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref33","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","author":"Wang","year":"2020","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zagoruyko","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/130"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_26"},{"key":"ref40","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247730.pdf?arnumber=11247730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:39:00Z","timestamp":1766061540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247730","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}