{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:59:48Z","timestamp":1777874388984,"version":"3.51.4"},"reference-count":98,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176255"],"award-info":[{"award-number":["62176255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01846","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19850-19861","source":"Crossref","is-referenced-by-count":0,"title":["ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking"],"prefix":"10.1109","author":[{"given":"Xiaokun","family":"Feng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Physical and Mathematical Sciences, NTU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuchen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dailing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiqi","family":"Wu","sequence":"additional","affiliation":[{"name":"CASIA,The Key Laboratory of Cognition and Decision Intelligence for Complex Systems"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"CASIA,The Key Laboratory of Cognition and Decision Intelligence for Complex Systems"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"11","article-title":"Visual prompting: Modifying pixel space to adapt pre-trained models","author":"Bahng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01802"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1476"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref6","article-title":"Learning historical status prompt for accurate and robust visual tracking","author":"Cai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3758\/APP.72.5.1283"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref11","article-title":"Revealing the dark secrets of extremely large kernel convnets on robustness","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32223"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"issue":"7","key":"ref21","first-page":"8","article-title":"Robust visual object tracking with natural language region proposal network","volume":"1","author":"Feng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888064"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0476"},{"key":"ref26","article-title":"Narrlv: Towards a comprehensive narrative-centric evaluation for long video generation models","author":"Feng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Cstrack: Enhancing rgb-x tracking via compact spatiotemporal features","author":"Feng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref30","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Guo","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/130"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref33","first-page":"25007","article-title":"A multi-modal global instance tracking benchmark (mgit): Better locating target in complex spatio-temporal and causal relationship","volume-title":"the 37th Conference on Neural Information Processing Systems","author":"Hu","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153312"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01908-5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref37","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2217"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref44","first-page":"7283","article-title":"Dttlm-vlt: Diverse text generation for visual language tracking based on 11 m","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2024"},{"key":"ref45","article-title":"Dtvlt: A multi-modal diverse text benchmark for visual language tracking based on 11m","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"How texts help? a finegrained evaluation to reveal the role of language in visionlanguage tracking","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Visual language tracking with multi-modal interaction: A robust benchmark","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"4931","article-title":"Crossmodal target retrieval for tracking by natural language","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01216"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref53","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01288"},{"key":"ref55","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446122"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4157"},{"key":"ref62","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref67","first-page":"39303","article-title":"Chattracker: Enhancing visual tracking performance via chatting with multimodal large language model","volume":"37","author":"Sun","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref68","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"33","author":"Tian","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429508"},{"key":"ref70","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28352"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288353"},{"key":"ref75","article-title":"Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking","author":"Wang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref80","article-title":"Autoregressive queries for adaptive tracking with spatiotemporaltransformers","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32954"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0086"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395352"},{"key":"ref90","article-title":"Hivit: A simpler and more efficient design of hierarchical vision transformer","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang","year":"2022"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.02.023"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01937-0"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212987"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33155"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443366.pdf?arnumber=11443366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:45:06Z","timestamp":1777578306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01846","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}