{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:21:16Z","timestamp":1783106476157,"version":"3.54.6"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2026AFB685"],"award-info":[{"award-number":["2026AFB685"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92367201"],"award-info":[{"award-number":["92367201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472331"],"award-info":[{"award-number":["62472331"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302349"],"award-info":[{"award-number":["62302349"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133081","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T15:34:16Z","timestamp":1780155256000},"page":"133081","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Decoupled appearance-trajectory deep tracking"],"prefix":"10.1016","volume":"330","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0045-1357","authenticated-orcid":false,"given":"Kai","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1988-7381","authenticated-orcid":false,"given":"Zeqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2318-8733","authenticated-orcid":false,"given":"Mengting","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8678-253X","authenticated-orcid":false,"given":"Wentao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4933-6259","authenticated-orcid":false,"given":"Aiwu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133081_bib0001","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19048","article-title":"ARTrackV2: Prompting autoregressive tracker where to look and how to describe","author":"Bai","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0002","series-title":"Proceedings of the European conference on computer vision","first-page":"205","article-title":"Know your surroundings: Exploiting scene information for object tracking","author":"Bhat","year":"2020"},{"key":"10.1016\/j.eswa.2026.133081_bib0003","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19258","article-title":"Hiptrack: Visual tracking with historical prompts","author":"Cai","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16871","article-title":"SPMTrack: Spatio-temporal parameter-efficient fine-tuning with mixture of experts for scalable visual tracking","author":"Cai","year":"2025"},{"key":"10.1016\/j.eswa.2026.133081_bib0005","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9589","article-title":"Robust object modeling for visual tracking","author":"Cai","year":"2023"},{"key":"10.1016\/j.eswa.2026.133081_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127450","article-title":"CasRPN: Cascade region proposal network for visual tracking","volume":"280","author":"Chen","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133081_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14572","article-title":"SeqTrack: Sequence to sequence learning for visual object tracking","author":"Chen","year":"2023"},{"key":"10.1016\/j.eswa.2026.133081_bib0008","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8126","article-title":"Transformer tracking","author":"Chen","year":"2021"},{"key":"10.1016\/j.eswa.2026.133081_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13608","article-title":"Mixformer: End-to-end tracking with iterative mixed attention","author":"Cui","year":"2022"},{"key":"10.1016\/j.eswa.2026.133081_bib0010","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint10.48550\/arXiv.2010.11929."},{"key":"10.1016\/j.eswa.2026.133081_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5374","article-title":"LaSOT: A high-quality benchmark for large-scale single object tracking","author":"Fan","year":"2019"},{"key":"10.1016\/j.eswa.2026.133081_bib0012","series-title":"Proceedings of the European conference on computer vision","first-page":"146","article-title":"AiATrack: Attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"key":"10.1016\/j.eswa.2026.133081_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18686","article-title":"Generalized relation modeling for transformer tracking","author":"Gao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133081_bib0014","unstructured":"Gevorgyan, Z. (2022). Siou loss: More powerful learning for bounding box regression. arXiv preprint10.48550\/arXiv.2205.12740."},{"key":"10.1016\/j.eswa.2026.133081_bib0015","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"773","article-title":"Target-aware tracking with long-term context attention","volume":"vol. 37","author":"He","year":"2023"},{"issue":"5","key":"10.1016\/j.eswa.2026.133081_bib0016","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","article-title":"GOT-10k: A large high-diversity benchmark for generic object tracking in the wild","volume":"43","author":"Huang","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133081_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19038","article-title":"RTracker: Recoverable tracking via PN tree structured memory","author":"Huang","year":"2024"},{"issue":"5","key":"10.1016\/j.eswa.2026.133081_bib0018","first-page":"6552","article-title":"Visual object tracking with discriminative filters and siamese networks: A survey and outlook","volume":"45","author":"Javed","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133081_bib0019","first-page":"35","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"Transactions of the American Society of Mechanical Engineers"},{"key":"10.1016\/j.eswa.2026.133081_bib0020","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1125","article-title":"Need for speed: A benchmark for higher frame rate object tracking","author":"Kiani Galoogahi","year":"2017"},{"key":"10.1016\/j.eswa.2026.133081_bib0021","doi-asserted-by":"crossref","unstructured":"Kou, Y., Gao, J., Li, B., Wang, G., Hu, W., Wang, Y., & Li, L. (2023). ZoomTrack: Target-aware non-uniform resizing for efficient visual tracking. Advances in Neural Information Processing Systems, 36, 50959\u201350977. 10.48550\/arXiv.2310.10071.","DOI":"10.52202\/075280-2217"},{"key":"10.1016\/j.eswa.2026.133081_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4282","article-title":"SiamRPN++: Evolution of siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.eswa.2026.133081_bib0023","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4986","article-title":"MambaLCT: Boosting tracking via long-term context state space model","volume":"vol. 39","author":"Li","year":"2025"},{"issue":"8","key":"10.1016\/j.eswa.2026.133081_bib0024","doi-asserted-by":"crossref","first-page":"7284","DOI":"10.1109\/TCSVT.2024.3377379","article-title":"Joint spatio-temporal similarity and discrimination learning for visual tracking","volume":"34","author":"Liang","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133081_bib0025","series-title":"Proceedings of the European conference on computer vision","first-page":"300","article-title":"Tracking meets LoRA: Faster training, larger model, stronger performance","author":"Lin","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0026","doi-asserted-by":"crossref","first-page":"16743","DOI":"10.52202\/068431-1218","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133081_bib0027","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.eswa.2026.133081_bib0028","article-title":"DPTrack: Dual-prompt guided network for visual object tracking","volume":"296","author":"Liu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133081_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8731","article-title":"MambaVLT: Time-evolving multimodal state space model for vision-language tracking","author":"Liu","year":"2025"},{"key":"10.1016\/j.eswa.2026.133081_bib0030","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint10.48550\/arXiv.1711.05101."},{"key":"10.1016\/j.eswa.2026.133081_bib0031","series-title":"Proceedings of the European conference on computer vision","first-page":"445","article-title":"A benchmark and simulator for UAV tracking","author":"Mueller","year":"2016"},{"key":"10.1016\/j.eswa.2026.133081_bib0032","series-title":"Proceedings of the European conference on computer vision","first-page":"300","article-title":"TrackingNet: A large-scale dataset and benchmark for object tracking in the wild","author":"Muller","year":"2018"},{"key":"10.1016\/j.eswa.2026.133081_bib0033","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"658","article-title":"Generalized intersection over union: A metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.1016\/j.eswa.2026.133081_bib0034","article-title":"FSTrack: Visual tracking with feature fusion and adaptive selection","volume":"298","author":"Shi","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133081_bib0035","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4838","article-title":"Explicit visual prompts for visual object tracking","volume":"vol. 38","author":"Shi","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0036","article-title":"MCTrack: Multi-cue spatio-temporal object tracking","volume":"299","author":"Song","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133081_bib0037","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2321","article-title":"Compact transformer tracker with correlative masked modeling","volume":"vol. 37","author":"Song","year":"2023"},{"key":"10.1016\/j.eswa.2026.133081_bib0038","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. 10.48550\/arXiv.1706.03762."},{"key":"10.1016\/j.eswa.2026.133081_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"24255","article-title":"A distractor-aware memory for visual object tracking with SAM2","author":"Videnovic","year":"2025"},{"key":"10.1016\/j.eswa.2026.133081_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6578","article-title":"Siam r-CNN: Visual tracking by re-detection","author":"Voigtlaender","year":"2020"},{"key":"10.1016\/j.eswa.2026.133081_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1571","article-title":"Transformer meets tracker: Exploiting temporal context for robust visual tracking","author":"Wang","year":"2021"},{"key":"10.1016\/j.eswa.2026.133081_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13763","article-title":"Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark","author":"Wang","year":"2021"},{"key":"10.1016\/j.eswa.2026.133081_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9697","article-title":"Autoregressive visual tracking","author":"Wei","year":"2023"},{"key":"10.1016\/j.eswa.2026.133081_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14561","article-title":"DropMAE: Masked autoencoders with spatial-attention dropout for tracking tasks","author":"Wu","year":"2023"},{"issue":"9","key":"10.1016\/j.eswa.2026.133081_bib0045","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","article-title":"Object tracking benchmark","volume":"37","author":"Wu","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133081_bib0046","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"4082","article-title":"MambaTrack: A simple baseline for multiple object tracking with state space model","author":"Xiao","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0047","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8727","article-title":"Robust tracking via mamba-based context-aware token learning","volume":"vol. 39","author":"Xie","year":"2025"},{"key":"10.1016\/j.eswa.2026.133081_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19300","article-title":"Autoregressive queries for adaptive tracking with spatio-temporal transformers","author":"Xie","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0049","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12549","article-title":"SiamFC++: Towards robust and accurate visual tracking with target estimation guidelines","volume":"vol. 34","author":"Xu","year":"2020"},{"key":"10.1016\/j.eswa.2026.133081_bib0049a","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10448","article-title":"Learning spatio-temporal transformer for visual tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.eswa.2026.133081_bib0050","unstructured":"Yang, C.-Y., Huang, H.-W., Chai, W., Jiang, Z., & Hwang, J.-N. (2024). SAMURAI: Adapting segment anything model for zero-shot visual tracking with motion-aware memory. arXiv preprint10.48550\/arXiv.2411.11922."},{"key":"10.1016\/j.eswa.2026.133081_bib0051","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1109\/TMM.2021.3074239","article-title":"SiamCorners: Siamese corner networks for visual tracking","volume":"24","author":"Yang","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.133081_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106079","article-title":"SiamAtt: Siamese attention network for visual tracking","volume":"203","author":"Yang","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133081_bib0053","series-title":"Proceedings of the European conference on computer vision","first-page":"341","article-title":"Joint feature learning and relation modeling for tracking: A one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.eswa.2026.133081_bib0054","doi-asserted-by":"crossref","first-page":"2629","DOI":"10.52202\/079017-0086","article-title":"Beyond accuracy: Tracking more like human via visual search","volume":"37","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133081_bib0055","unstructured":"Zhao, J., Chen, X., Yuan, Y., Felsberg, M., Wang, D., & Lu, H. (2025). Efficient motion prompt learning for robust visual tracking. arXiv preprint10.48550\/arXiv.2505.16321."},{"key":"10.1016\/j.eswa.2026.133081_bib0056","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10635","article-title":"Decoupled spatio-temporal consistency learning for self-supervised tracking","volume":"vol. 39","author":"Zheng","year":"2025"},{"key":"10.1016\/j.eswa.2026.133081_bib0057","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7588","article-title":"ODTrack: Online dense temporal token learning for visual tracking","volume":"vol. 38","author":"Zheng","year":"2024"},{"key":"10.1016\/j.eswa.2026.133081_bib0058","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12993","article-title":"Distance-IoU loss: Faster and better learning for bounding box regression","volume":"vol. 34","author":"Zheng","year":"2020"},{"issue":"8","key":"10.1016\/j.eswa.2026.133081_bib0059","doi-asserted-by":"crossref","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","article-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","volume":"52","author":"Zheng","year":"2021","journal-title":"IEEE Transactions on Cybernetics"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426019925?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426019925?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:03:51Z","timestamp":1783105431000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426019925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":60,"alternative-id":["S0957417426019925"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133081","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Decoupled appearance-trajectory deep tracking","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133081","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133081"}}