{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T23:46:08Z","timestamp":1782344768116,"version":"3.54.5"},"reference-count":112,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ipm.2026.104975","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T13:43:55Z","timestamp":1782135835000},"page":"104975","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["RELTrack: A language-guided RGB-event object tracking framework"],"prefix":"10.1016","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9682-8462","authenticated-orcid":false,"given":"Sara","family":"Alansari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ameena Saad","family":"Al-Sumaiti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khalifa Hassan Al","family":"Hosani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Fawad","family":"Hussain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104975_b1","doi-asserted-by":"crossref","first-page":"31351","DOI":"10.1109\/ACCESS.2025.3540445","article-title":"ELTrack: events-language description for visual object tracking","volume":"13","author":"Alansari","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.ipm.2026.104975_b2","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhao, Z., Gong, Y., & Wei, X. (2024). Artrackv2: Prompting autoregressive tracker where to look and how to describe. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19048\u201319057).","DOI":"10.1109\/CVPR52733.2024.01802"},{"key":"10.1016\/j.ipm.2026.104975_b3","series-title":"Computer vision \u2013 ECCV 2016 workshops","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.ipm.2026.104975_b4","series-title":"2019 IEEE\/CVF international conference on computer vision","first-page":"6181","article-title":"Learning discriminative model prediction for tracking","author":"Bhat","year":"2019"},{"key":"10.1016\/j.ipm.2026.104975_b5","series-title":"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.ipm.2026.104975_b6","series-title":"WACV","first-page":"1571","article-title":"Efficient visual tracking with exemplar transformers","author":"Blatter","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b7","doi-asserted-by":"crossref","unstructured":"Cai, Y., Liu, J., Tang, J., & Wu, G. (2023). Robust object modeling for visual tracking. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9589\u20139600).","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"10.1016\/j.ipm.2026.104975_b8","doi-asserted-by":"crossref","unstructured":"Cai, W., Liu, Q., & Wang, Y. (2024). Hiptrack: Visual tracking with historical prompts. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19258\u201319267).","DOI":"10.1109\/CVPR52733.2024.01822"},{"issue":"2","key":"10.1016\/j.ipm.2026.104975_b9","doi-asserted-by":"crossref","first-page":"2239","DOI":"10.1609\/aaai.v39i2.32223","article-title":"SUTrack: Towards simple and unified single object tracking","volume":"39","author":"Chen","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.ipm.2026.104975_b10","series-title":"European conference on computer vision","first-page":"375","article-title":"Backbone is all your need: A simplified architecture for visual object tracking","author":"Chen","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b11","doi-asserted-by":"crossref","unstructured":"Chen, X., Peng, H., Wang, D., Lu, H., & Hu, H. (2023). Seqtrack: Sequence to sequence learning for visual object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14572\u201314581).","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"10.1016\/j.ipm.2026.104975_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2022.103508","article-title":"Visual object tracking: A survey","volume":"222","author":"Chen","year":"2022","journal-title":"Computer Vision and Image Understanding"},{"key":"10.1016\/j.ipm.2026.104975_b13","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., & Lu, H. (2021). Transformer Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8126\u20138135).","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10.1016\/j.ipm.2026.104975_b14","series-title":"CVPR","article-title":"SiamBAN: Siamese box adaptive network for visual tracking","author":"Chen","year":"2020"},{"key":"10.1016\/j.ipm.2026.104975_b15","series-title":"CVPR","article-title":"ADSTrack: Target-aware tracker with adaptive sampling","author":"Chen","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b16","series-title":"How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites","author":"Chen","year":"2024"},{"key":"10.1016\/j.ipm.2026.104975_b17","series-title":"Robust long-term object tracking via improved discriminative model prediction","author":"Choi","year":"2020"},{"key":"10.1016\/j.ipm.2026.104975_b18","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., & Wu, G. (2022). MixFormer: End-to-End Tracking With Iterative Mixed Attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13608\u201313618).","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"10.1016\/j.ipm.2026.104975_b19","series-title":"CVPR","first-page":"13608","article-title":"Mixformer: End-to-end tracking with iterative mixed attention","author":"Cui","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b20","doi-asserted-by":"crossref","unstructured":"Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., & Yang, X. (2020). High-Performance Long-Term Tracking with Meta-Updater. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"10.1016\/j.ipm.2026.104975_b21","series-title":"2019 IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4655","article-title":"ATOM: Accurate tracking by overlap maximization","author":"Danelljan","year":"2019"},{"key":"10.1016\/j.ipm.2026.104975_b22","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L. V., & Timofte, R. (2020). Probabilistic Regression for Visual Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"10.1016\/j.ipm.2026.104975_b23","series-title":"CVPR","article-title":"ECO: Efficient convolution operators for tracking","author":"Danelljan","year":"2017"},{"key":"10.1016\/j.ipm.2026.104975_b24","series-title":"NAACL","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.ipm.2026.104975_b25","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J., Shao, L., & Porikli, F. (2020). CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers. In European conference on computer vision.","DOI":"10.1007\/978-3-030-58565-5_23"},{"key":"10.1016\/j.ipm.2026.104975_b26","series-title":"ICLR","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b27","doi-asserted-by":"crossref","unstructured":"Du, H., Wu, B., Lu, Y., & Mao, Z. (2025). SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation. In Proceedings of the computer vision and pattern recognition conference (pp. 13798\u201313809).","DOI":"10.1109\/CVPR52734.2025.01288"},{"issue":"3","key":"10.1016\/j.ipm.2026.104975_b28","doi-asserted-by":"crossref","DOI":"10.1117\/1.OE.62.3.031209","article-title":"High-temporal-resolution event-based vehicle detection and tracking","volume":"62","author":"El Shair","year":"2023","journal-title":"Optical Engineering"},{"issue":"2","key":"10.1016\/j.ipm.2026.104975_b29","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","article-title":"Lasot: A high-quality large-scale single object tracking benchmark","volume":"129","author":"Fan","year":"2021","journal-title":"IJCV"},{"key":"10.1016\/j.ipm.2026.104975_b30","series-title":"CVPR","article-title":"Learning a discriminative siamese tracker with natural language supervision","author":"Feng","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b31","series-title":"CVPR","first-page":"5851","article-title":"Siamese natural language tracker: Tracking by natural language descriptions with siamese trackers","author":"Feng","year":"2021"},{"issue":"1","key":"10.1016\/j.ipm.2026.104975_b32","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: A survey","volume":"44","author":"Gallego","year":"2022","journal-title":"PAMI"},{"key":"10.1016\/j.ipm.2026.104975_b33","series-title":"Computer vision \u2013 ECCV 2022","first-page":"146","article-title":"AiATrack: Attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b34","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., & Zhang, J. (2023). Generalized relation modeling for transformer tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18686\u201318695).","DOI":"10.1109\/CVPR52729.2023.01792"},{"issue":"2","key":"10.1016\/j.ipm.2026.104975_b35","doi-asserted-by":"crossref","first-page":"2822","DOI":"10.1109\/LRA.2021.3060707","article-title":"Combining events and frames using recurrent asynchronous multimodal networks for monocular depth prediction","volume":"6","author":"Gehrig","year":"2021","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.ipm.2026.104975_b36","series-title":"CVPR","article-title":"SiamCAR: Siamese fully convolutional classification and regression for visual tracking","author":"Guo","year":"2020"},{"key":"10.1016\/j.ipm.2026.104975_b37","series-title":"CVPR","first-page":"9543","article-title":"Graph attention tracking","author":"Guo","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b38","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked Autoencoders Are Scalable Vision Learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.ipm.2026.104975_b39","doi-asserted-by":"crossref","unstructured":"Hong, L., Yan, S., Zhang, R., Li, W., Zhou, X., Guo, P., Jiang, K., Chen, Y., Li, J., Chen, Z., & Zhang, W. (2024). OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19079\u201319091).","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"10.1016\/j.ipm.2026.104975_b40","series-title":"2024 IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26541","article-title":"SDSTrack: Self-distillation symmetric adapter learning for multi-modal visual object tracking","author":"Hou","year":"2024"},{"key":"10.1016\/j.ipm.2026.104975_b41","series-title":"MTNet: Learning modality-aware representation with transformer for RGBT tracking","author":"Hou","year":"2025"},{"key":"10.1016\/j.ipm.2026.104975_b42","series-title":"Pattern recognition and computer vision","first-page":"3","article-title":"Mamba-FETrack: Frame-event tracking via state space model","author":"Huang","year":"2025"},{"issue":"5","key":"10.1016\/j.ipm.2026.104975_b43","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":"PAMI"},{"issue":"5","key":"10.1016\/j.ipm.2026.104975_b44","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 TPAMI"},{"key":"10.1016\/j.ipm.2026.104975_b45","series-title":"KDD \u201922","article-title":"Learned token pruning for efficient transformer inference","author":"Kim","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b46","series-title":"ECCV","first-page":"380","article-title":"Hard occlusions in visual object tracking","volume":"Vol. 12550","author":"Kuipers","year":"2020"},{"key":"10.1016\/j.ipm.2026.104975_b47","series-title":"2018 IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8971","article-title":"High performance visual tracking with siamese region proposal network","author":"Li","year":"2018"},{"key":"10.1016\/j.ipm.2026.104975_b48","series-title":"CVPR","article-title":"SiamRPN++: Evolution of siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.ipm.2026.104975_b49","series-title":"ICML","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b50","series-title":"NeurIPS","article-title":"Mono3DVLT: Language-driven monocular 3D visual object tracking","author":"Li","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b51","series-title":"CFTrack: Enhancing lightweight visual tracking through contrastive learning and feature matching","author":"Liang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104975_b52","series-title":"ICCV","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.ipm.2026.104975_b53","series-title":"ICCV","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b54","series-title":"Revisiting token pruning for object detection and instance segmentation","author":"Liu","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b55","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s00371-025-04309-6","article-title":"UREPtrack: single-branch PoolFormer for unified attention-free RGB-event visual object tracking","volume":"42","author":"Lu","year":"2026","journal-title":"Visual Computer"},{"key":"10.1016\/j.ipm.2026.104975_b56","series-title":"All-in-one: Exploring unified vision-language tracking with multi-modal alignment","author":"Luo","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b57","series-title":"CVPR","article-title":"Event-based vision meets deep learning on steering prediction for self-driving cars","author":"Maqueda","year":"2018"},{"key":"10.1016\/j.ipm.2026.104975_b58","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Bhat, G., Paul, M., Paudel, D. P., Yu, F., & Van Gool, L. (2022). Transforming Model Prediction for Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8731\u20138740).","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"10.1016\/j.ipm.2026.104975_b59","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D. P., & Van Gool, L. (2021). Learning Target Candidate Association To Keep Track of What Not To Track. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 13444\u201313454).","DOI":"10.1109\/ICCV48922.2021.01319"},{"issue":"2","key":"10.1016\/j.ipm.2026.104975_b60","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1177\/0278364917691115","article-title":"The event-camera dataset and simulator: Event-based data for pose estimation, visual odometry, and SLAM","volume":"36","author":"Mueggler","year":"2017","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.ipm.2026.104975_b61","series-title":"ICML","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010"},{"key":"10.1016\/j.ipm.2026.104975_b62","doi-asserted-by":"crossref","unstructured":"Nam, H., & Han, B. (2016). Learning Multi-Domain Convolutional Neural Networks for Visual Tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.465"},{"key":"10.1016\/j.ipm.2026.104975_b63","series-title":"GPT-4 technical report","author":"OpenAI","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b64","series-title":"Computer vision \u2013 ECCV 2022","first-page":"571","article-title":"Robust visual tracking by segmentation","author":"Paul","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b65","doi-asserted-by":"crossref","unstructured":"Qin, H., Xu, T., Li, T., Chen, Z., Feng, T., & Li, J. (2025). MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking. In Proceedings of the computer vision and pattern recognition conference (pp. 16882\u201316891).","DOI":"10.1109\/CVPR52734.2025.01573"},{"key":"10.1016\/j.ipm.2026.104975_b66","series-title":"CVPR","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.ipm.2026.104975_b67","unstructured":"Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In Proceedings of the 5th workshop on energy efficient machine learning and cognitive computing."},{"key":"10.1016\/j.ipm.2026.104975_b68","first-page":"4838","article-title":"Explicit visual prompts for visual object tracking","volume":"Vol. 38","author":"Shi","year":"2024"},{"issue":"5","key":"10.1016\/j.ipm.2026.104975_b69","doi-asserted-by":"crossref","first-page":"4838","DOI":"10.1609\/aaai.v38i5.28286","article-title":"Explicit visual prompts for visual object tracking","volume":"38","author":"Shi","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.ipm.2026.104975_b70","doi-asserted-by":"crossref","unstructured":"Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Lau, R. W., & Yang, M.-H. (2018). VITAL: VIsual Tracking via Adversarial Learning. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00937"},{"key":"10.1016\/j.ipm.2026.104975_b71","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., & Zhou, D. (2020). MobileBERT: a compact task-agnostic BERT for resource-limited devices. In Proceedings of the 58th annual meeting of the association for computational linguistics (pp. 2158\u20132170).","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"10.1016\/j.ipm.2026.104975_b72","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112718","article-title":"Revisiting color-event based tracking: A unified network, dataset, and metric","volume":"172","author":"Tang","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.ipm.2026.104975_b73","series-title":"ICCV","article-title":"EventTrack: Learning to track with asynchronous event-based data","author":"Tang","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b74","series-title":"Revisiting color-event based tracking: A unified network, dataset, and metric","author":"Tang","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b75","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P. H., & Leibe, B. (2020). Siam R-CNN: Visual Tracking by Re-Detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"10.1016\/j.ipm.2026.104975_b76","series-title":"Long-term frame-event visual tracking: Benchmark dataset and baseline","author":"Wang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104975_b77","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, S., Tang, C., Zhu, L., Jiang, B., Tian, Y., & Tang, J. (2024). Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19248\u201319257).","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"10.1016\/j.ipm.2026.104975_b78","first-page":"1","article-title":"Modality interaction decoupling: Spatiotemporal memory-driven unified multimodal tracking framework","author":"Wang","year":"2026","journal-title":"IEEE Internet of Things Journal"},{"issue":"1","key":"10.1016\/j.ipm.2026.104975_b79","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1109\/TCSVT.2025.3588533","article-title":"MambaEVT: Event stream-based visual object tracking using state space model","volume":"36","author":"Wang","year":"2026","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.ipm.2026.104975_b80","series-title":"Decoupling amplitude and phase attention in frequency domain for RGB-event based visual object tracking","author":"Wang","year":"2026"},{"key":"10.1016\/j.ipm.2026.104975_b81","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., & Li, H. (2021). Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1571\u20131580).","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"10.1016\/j.ipm.2026.104975_b82","series-title":"CVPR","article-title":"Fast online object tracking and segmentation: A unifying approach","author":"Wang","year":"2019"},{"key":"10.1016\/j.ipm.2026.104975_b83","series-title":"CVPR","first-page":"13763","article-title":"Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark","author":"Wang","year":"2021"},{"issue":"3","key":"10.1016\/j.ipm.2026.104975_b84","doi-asserted-by":"crossref","first-page":"1997","DOI":"10.1109\/TCYB.2023.3318601","article-title":"Visevent: Reliable object tracking via collaboration of frame and event flows","volume":"54","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.ipm.2026.104975_b85","series-title":"2023 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.ipm.2026.104975_b86","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wang, X., Yang, X., Liu, M., Zeng, D., Ye, H., & Li, S. (2025). Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking. In Proceedings of the computer vision and pattern recognition conference (pp. 17103\u201317113).","DOI":"10.1109\/CVPR52734.2025.01594"},{"key":"10.1016\/j.ipm.2026.104975_b87","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zheng, J., Ren, X., Vasluianu, F.-A., Ma, C., Paudel, D. P., Van Gool, L., & Timofte, R. (2024). Single-Model and Any-Modality for Video Object Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19156\u201319166).","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"10.1016\/j.ipm.2026.104975_b88","doi-asserted-by":"crossref","unstructured":"Xie, J., Zhong, B., Mo, Z., Zhang, S., Shi, L., Song, S., & Ji, R. (2024). Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19300\u201319309).","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"10.1016\/j.ipm.2026.104975_b89","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113532","article-title":"Learning frequency and memory-aware prompts for multi-modal object tracking","author":"Xu","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.ipm.2026.104975_b90","first-page":"8824","article-title":"Less is more: Token context-aware learning for object tracking","volume":"Vol. 39","author":"Xu","year":"2025"},{"key":"10.1016\/j.ipm.2026.104975_b91","series-title":"ICCV","first-page":"10448","article-title":"Learning spatio-temporal transformer for visual tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b92","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"3492","article-title":"Prompting for multi-modal tracking","author":"Yang","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b93","series-title":"CVPR","first-page":"15671","article-title":"Vision-language pre-training with triple contrastive learning","author":"Yang","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b94","series-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104975_b95","series-title":"Joint feature learning and relation modeling for tracking: A one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.ipm.2026.104975_b96","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, Y., Liu, W., Li, M., Bai, J., Yin, B., & Yang, X. (2023). Frame-Event Alignment and Fusion Network for High Frame Rate Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9781\u20139790).","DOI":"10.1109\/CVPR52729.2023.00943"},{"issue":"2","key":"10.1016\/j.ipm.2026.104975_b97","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s11263-025-02666-2","article-title":"Efficient vision transformer with token sparsification for event-based object tracking","volume":"134","author":"Zhang","year":"2026","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"10.1016\/j.ipm.2026.104975_b98","doi-asserted-by":"crossref","first-page":"5847","DOI":"10.1109\/TPAMI.2025.3555485","article-title":"Cross-modality distillation for multi-modal tracking","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104975_b99","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1109\/TIP.2025.3533213","article-title":"Spiking neural networks with adaptive membrane time constant for event-based tracking","volume":"34","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.ipm.2026.104975_b100","series-title":"ICCV","first-page":"13043","article-title":"Object tracking by jointly exploiting frame and event domain","author":"Zhang","year":"2021"},{"key":"10.1016\/j.ipm.2026.104975_b101","series-title":"CVPR","article-title":"A benchmark for UAV-view natural language-guided tracking (UAVNLT)","author":"Zhang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104975_b102","series-title":"Sa2VA: Segment anything meets video adaptation for referring video object segmentation","author":"Zhao","year":"2024"},{"key":"10.1016\/j.ipm.2026.104975_b103","series-title":"ATSTrack: Enhancing visual-language tracking by aligning temporal and spatial scales","author":"Zhen","year":"2025"},{"key":"10.1016\/j.ipm.2026.104975_b104","series-title":"European conference on computer vision","first-page":"110","article-title":"Exploring the feature extraction and relation modeling for light-weight transformer tracking","author":"Zheng","year":"2024"},{"key":"10.1016\/j.ipm.2026.104975_b105","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.ipm.2026.104975_b106","series-title":"LLaFEA: Frame-event complementary fusion for fine-grained spatiotemporal understanding in LMMs","author":"Zhou","year":"2025"},{"issue":"3","key":"10.1016\/j.ipm.2026.104975_b107","doi-asserted-by":"crossref","DOI":"10.1145\/3795518","article-title":"An efficient hybrid cascade tracker with spiking neural networks for event domain tracking","volume":"22","author":"Zhou","year":"2026","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"10.1016\/j.ipm.2026.104975_b108","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Hou, J., & Wu, D. O. (2023). Cross-Modal Orthogonal High-Rank Augmentation for RGB-Event Transformer-Trackers. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22045\u201322055).","DOI":"10.1109\/ICCV51070.2023.02015"},{"key":"10.1016\/j.ipm.2026.104975_b109","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., & Lu, H. (2023). Visual Prompt Multi-Modal Tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9516\u20139526).","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"10.1016\/j.ipm.2026.104975_b110","first-page":"10959","article-title":"Two-stream beats one-stream: asymmetric siamese network for efficient visual tracking","volume":"Vol. 39","author":"Zhu","year":"2025"},{"key":"10.1016\/j.ipm.2026.104975_b111","series-title":"CVPR","first-page":"5816","article-title":"Event-based visual inertial odometry","author":"Zhu","year":"2017"},{"key":"10.1016\/j.ipm.2026.104975_b112","series-title":"CVPR","article-title":"Unsupervised event-based learning of optical flow, depth, and egomotion","author":"Zhu","year":"2019"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003663?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003663?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T22:47:06Z","timestamp":1782341226000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326003663"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":112,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2027,1]]}},"alternative-id":["S0306457326003663"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104975","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RELTrack: A language-guided RGB-event object tracking framework","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104975","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"104975"}}