{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:14Z","timestamp":1777568474024,"version":"3.51.4"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888064","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues"],"prefix":"10.1109","author":[{"given":"Xiaokun","family":"Feng","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dailing","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Physical and Mathematical Sciences,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuchen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiqi","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01908-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01937-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref6","article-title":"A multi-modal global instance tracking benchmark (mgit): Better locating target in complex spatio-temporal and causal relationship","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Hu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00724"},{"key":"ref8","article-title":"How texts help? a fine-grained evaluation to reveal the role of language in vision-language tracking","author":"Li","year":"2024"},{"key":"ref9","article-title":"Memvlt: Vision-language tracking with adaptive memory-based prompts","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Feng"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01069"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446122"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395352"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref24","article-title":"Beyond accuracy: Tracking more like human via visual search","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8462-6_20"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"issue":"7","key":"ref29","first-page":"8","article-title":"Robust visual object tracking with natural language region proposal network","volume":"1","author":"Feng","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref33","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"35","author":"Guo"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.02.023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288353"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01288"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref40","article-title":"Revealing the dark secrets of extremely large kernel convnets on robustness","author":"Chen","year":"2024"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888064.pdf?arnumber=10888064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:08Z","timestamp":1774416128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888064","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}