{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:05:27Z","timestamp":1784203527796,"version":"3.55.0"},"reference-count":84,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"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"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109052","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:53:09Z","timestamp":1777564389000},"page":"109052","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Not all regions are equal: Spatially adaptive representation learning for efficient visual object tracking"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5419-5071","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-3013","authenticated-orcid":false,"given":"Shan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-0650","authenticated-orcid":false,"given":"Hongke","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8823-0833","authenticated-orcid":false,"given":"Zhanwen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5499-5013","authenticated-orcid":false,"given":"Dejun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0429-0263","authenticated-orcid":false,"given":"Longguang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109052_bib0001","series-title":"Proc. eur. conf. comput. vis. (ECCV)","article-title":"A benchmark and simulator for UAV tracking","author":"Benchmark","year":"2016"},{"key":"10.1016\/j.neunet.2026.109052_bib0002","series-title":"Proc. eur. conf. comput. vis. (ECCV)","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.neunet.2026.109052_bib0003","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"6182","article-title":"Learning discriminative model prediction for tracking","author":"Bhat","year":"2019"},{"key":"10.1016\/j.neunet.2026.109052_bib0004","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"9589","article-title":"Robust object modeling for visual tracking","author":"Cai","year":"2023"},{"key":"10.1016\/j.neunet.2026.109052_bib0005","series-title":"Proc. eur. conf. comput. vis. (ECCV)","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.neunet.2026.109052_bib0006","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"14572","article-title":"Seqtrack: Sequence to sequence learning for visual object tracking","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109052_bib0007","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"8126","article-title":"Transformer tracking","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0008","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"13608","article-title":"Mixformer: End-to-end tracking with iterative mixed attention","author":"Cui","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0009","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit.(CVPR)","first-page":"4660","article-title":"Atom: Accurate tracking by overlap maximization","author":"Danelljan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109052_bib0010","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"6638","article-title":"Eco: Efficient convolution operators for tracking","author":"Danelljan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109052_bib0011","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2026.109052_bib0012","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"6569","article-title":"Centernet: Keypoint triplets for object detection","author":"Duan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109052_bib0013","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., & Ling, H. (2019). Lasot: A high-quality benchmark for large-scale single object tracking. In Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR) (pp. 5374\u20135383).","DOI":"10.1109\/CVPR.2019.00552"},{"key":"10.1016\/j.neunet.2026.109052_bib0014","doi-asserted-by":"crossref","unstructured":"Fu, Z., Fu, Z., Liu, Q., Cai, W., & Wang, Y. (2022). Sparsett: Visual tracking with sparse transformers. arXiv: 2205.03776.","DOI":"10.24963\/ijcai.2022\/127"},{"issue":"4","key":"10.1016\/j.neunet.2026.109052_bib0015","doi-asserted-by":"crossref","first-page":"1612","DOI":"10.1109\/TITS.2019.2930337","article-title":"Manifold siamese network: A novel visual tracking convnet for autonomous vehicles","volume":"21","author":"Gao","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems(T-ITS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0016","series-title":"Proc. eur. conf. comput. vis. (ECCV)","first-page":"146","article-title":"Aiatrack: Attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0017","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"18686","article-title":"Generalized relation modeling for transformer tracking","author":"Gao","year":"2023"},{"issue":"5","key":"10.1016\/j.neunet.2026.109052_bib0018","doi-asserted-by":"crossref","first-page":"4192","DOI":"10.1109\/TITS.2023.3331143","article-title":"Efficient baselines for motion prediction in autonomous driving","volume":"25","author":"G\u00f3mez-Hu\u00e9lamo","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems(T-ITS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0019","unstructured":"Han, S., Mao, H., & Dally, W. J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv: 1510.00149."},{"key":"10.1016\/j.neunet.2026.109052_bib0020","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0021","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109052_bib0022","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"11936","article-title":"Rethinking spatial dimensions of vision transformers","author":"Heo","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0023","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"19079","article-title":"Onetracker: Unifying visual object tracking with foundation models and efficient tuning","author":"Hong","year":"2024"},{"issue":"5","key":"10.1016\/j.neunet.2026.109052_bib0024","doi-asserted-by":"crossref","first-page":"2852","DOI":"10.1109\/TPAMI.2023.3335338","article-title":"Anti-UAV410: A thermal infrared benchmark and customized scheme for tracking drones in the wild","volume":"46","author":"Huang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"10.1016\/j.neunet.2026.109052_bib0025","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 (TPAMI)"},{"key":"10.1016\/j.neunet.2026.109052_bib0026","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/TMM.2021.3128047","article-title":"Anti-UAV: A large-scale benchmark for vision-based UAV tracking","volume":"25","author":"Jiang","year":"2021","journal-title":"IEEE Transactions on Multimedia. (TMM)"},{"key":"10.1016\/j.neunet.2026.109052_bib0027","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0028","doi-asserted-by":"crossref","first-page":"6168","DOI":"10.1109\/TIP.2023.3329669","article-title":"Ncsiam: Reliable matching via neighborhood consensus for siamese-based object tracking","volume":"32","author":"Lai","year":"2023","journal-title":"IEEE Transactions on Image Processing(TIP)"},{"key":"10.1016\/j.neunet.2026.109052_bib0029","first-page":"1","article-title":"Target-aware transformer for satellite video object tracking","volume":"62","author":"Lai","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing(TGRS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0030","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"4282","article-title":"Siamrpn++: Evolution of siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2026.109052_bib0031","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"8971","article-title":"High performance visual tracking with siamese region proposal network","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.109052_bib0032","doi-asserted-by":"crossref","first-page":"12934","DOI":"10.52202\/068431-0940","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing System (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0033","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 Inf. Processing System (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0034","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.109052_bib0035","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2736","article-title":"Learning efficient convolutional networks through network slimming","author":"Liu","year":"2017"},{"key":"10.1016\/j.neunet.2026.109052_bib0036","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0037","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv: 1711.05101."},{"key":"10.1016\/j.neunet.2026.109052_bib0038","unstructured":"Mehta, S., & Rastegari, M. (2021). Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv: 2110.02178."},{"key":"10.1016\/j.neunet.2026.109052_bib0039","series-title":"Proc. eur. conf. comput. vis. (ECCV)","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.neunet.2026.109052_bib0040","doi-asserted-by":"crossref","first-page":"4308","DOI":"10.1109\/TMM.2023.3321497","article-title":"Robust tracking via bidirectional transduction with mask information","volume":"26","author":"Ning","year":"2023","journal-title":"IEEE Transactions on Multimedia. (TMM)"},{"key":"10.1016\/j.neunet.2026.109052_bib0041","first-page":"91","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 System (NeurIPS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0042","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (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.neunet.2026.109052_bib0043","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., & Zelnik-Manor, L. (2021). Imagenet-21k pretraining for the masses. arXiv: 2104.10972."},{"key":"10.1016\/j.neunet.2026.109052_bib0044","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neucom.2017.02.029","article-title":"Group sparse regularization for deep neural networks","volume":"241","author":"Scardapane","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109052_bib0045","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"8791","article-title":"Transformer tracking with cyclic shifting window attention","author":"Song","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0046","series-title":"Proc. int. conf. mach. learn. (ICML)","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109052_bib0047","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"1420","article-title":"Siamese instance search for tracking","author":"Tao","year":"2016"},{"key":"10.1016\/j.neunet.2026.109052_bib0048","unstructured":"Thangavel, J., Kokul, T., Ramanan, A., & Fernando, S.. Transformers in single object tracking: An experimental survey. arxiv 2023. arXiv: 2302.11867."},{"key":"10.1016\/j.neunet.2026.109052_bib0049","series-title":"Proc. eur. conf. comput. vis. (ECCV)","first-page":"459","article-title":"Maxvit: Multi-axis vision transformer","author":"Tu","year":"2022"},{"issue":"2","key":"10.1016\/j.neunet.2026.109052_bib0050","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1109\/TITS.2012.2187641","article-title":"Real-time computer vision\/DGPS-aided inertial navigation system for lane-level vehicle navigation","volume":"13","author":"Vu","year":"2012","journal-title":"IEEE Transactions on Intelligent Transportation Systems(T-ITS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0051","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"1571","article-title":"Transformer meets tracker: Exploiting temporal context for robust visual tracking","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0052","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"4854","article-title":"Learning attentions: Residual attentional siamese network for high performance online visual tracking","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109052_bib0053","doi-asserted-by":"crossref","first-page":"5073","DOI":"10.1109\/TIP.2024.3453028","article-title":"Modelling of multiple spatial-temporal relations for robust visual object tracking","volume":"33","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Image Processing(TIP)"},{"key":"10.1016\/j.neunet.2026.109052_bib0054","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"568","article-title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0055","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","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.neunet.2026.109052_bib0056","doi-asserted-by":"crossref","first-page":"2006","DOI":"10.1109\/TMM.2023.3291140","article-title":"Dynamic template updating using spatial-temporal information in siamese trackers","volume":"26","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Multimedia. (TMM)"},{"key":"10.1016\/j.neunet.2026.109052_bib0057","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"9697","article-title":"Autoregressive visual tracking","author":"Wei","year":"2023"},{"key":"10.1016\/j.neunet.2026.109052_bib0058","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume":"29","author":"Wen","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109052_bib0059","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","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.neunet.2026.109052_bib0060","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 Pattern Analysis Machine Intelligent (TPAMI)"},{"key":"10.1016\/j.neunet.2026.109052_bib0061","unstructured":"Xia, J., Shi, D., Song, K., Song, L., Wang, X., Jin, S., Zhou, L., Cheng, Y., Jin, L., Zhu, Z. et al. (2023a). Unified single-stage transformer network for efficient RGB-t tracking. arXiv: 2308.13764."},{"issue":"5","key":"10.1016\/j.neunet.2026.109052_bib0062","doi-asserted-by":"crossref","first-page":"5543","DOI":"10.1109\/TITS.2023.3243470","article-title":"A lightweight and detector-free 3d single object tracker on point clouds","volume":"24","author":"Xia","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems(T-ITS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0063","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"22826","article-title":"Videotrack: Learning to track objects via video transformer","author":"Xie","year":"2023"},{"key":"10.1016\/j.neunet.2026.109052_bib0064","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"2688","article-title":"Learning tracking representations via dual-branch fully transformer networks","author":"Xie","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0065","series-title":"Proc. eur. conf. comput. vis. (ECCV)","first-page":"733","article-title":"Towards grand unification of object tracking","author":"Yan","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0066","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"10448","article-title":"Learning spatio-temporal transformer for visual tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109052_bib0067","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/TCE.2023.3251407","article-title":"Bandt: A border-aware network with deformable transformers for visual tracking","volume":"69","author":"Yang","year":"2023","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.neunet.2026.109052_bib0068","series-title":"Proc. eur. conf. comput. vis. (ECCV)","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.neunet.2026.109052_bib0069","series-title":"Proc. IEEE\/CVF int. conf. comput. vis. (ICCV)","first-page":"9856","article-title":"High-performance discriminative tracking with transformers","author":"Yu","year":"2021"},{"issue":"4","key":"10.1016\/j.neunet.2026.109052_bib0070","doi-asserted-by":"crossref","first-page":"5656","DOI":"10.1109\/TNNLS.2022.3208605","article-title":"Learning dynamic compact memory embedding for deformable visual object tracking","volume":"35","author":"Yu","year":"2022","journal-title":"IEEE Transactions Neural Networks & Learning System (TNNLS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0071","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1109\/TMM.2023.3234372","article-title":"Domain adaptive transformer tracking under occlusions","volume":"25","author":"Yu","year":"2023","journal-title":"IEEE Transactions on Multimedia. (TMM)"},{"key":"10.1016\/j.neunet.2026.109052_bib0072","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109052_bib0073","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1109\/TMM.2023.3285441","article-title":"One-stream vision-language memory network for object tracking","volume":"26","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Multimedia. (TMM)"},{"key":"10.1016\/j.neunet.2026.109052_bib0074","doi-asserted-by":"crossref","first-page":"1900","DOI":"10.1109\/TITS.2024.3512551","article-title":"SiamTFA: Siamese triple-stream feature aggregation network for efficient RGBT tracking","volume":"26","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems(T-ITS)"},{"issue":"9","key":"10.1016\/j.neunet.2026.109052_bib0075","doi-asserted-by":"crossref","first-page":"14148","DOI":"10.1109\/TITS.2022.3147770","article-title":"Monocular visual traffic surveillance: A review","volume":"23","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems(T-ITS)"},{"key":"10.1016\/j.neunet.2026.109052_bib0076","series-title":"2023\u202fIEEE International conference on image processing (ICIP)","first-page":"1975","article-title":"Modality meets long-term tracker: A siamese dual fusion framework for tracking UAV","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109052_bib0077","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"4591","article-title":"Deeper and wider siamese networks for real-time visual tracking","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neunet.2026.109052_bib0078","series-title":"Proc. eur. conf. comput. vis. (ECCV)","first-page":"771","article-title":"Ocean: Object-aware anchor-free tracking","author":"Zhang","year":"2020"},{"issue":"8","key":"10.1016\/j.neunet.2026.109052_bib0079","first-page":"1","article-title":"Review and analysis of rgbt single object tracking methods: A fusion perspective","volume":"20","author":"Zhang","year":"2024","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.neunet.2026.109052_bib0080","series-title":"Proc. conf. artif. intell. (AAAI)","first-page":"3417","article-title":"Nested hierarchical transformer: Towards accurate, data-efficient and interpretable visual understanding","volume":"vol. 36","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0081","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"18696","article-title":"Representation learning for visual object tracking by masked appearance transfer","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109052_bib0082","series-title":"Int. conf. artif. neur. net (ICANN)","first-page":"85","article-title":"Correlation-based transformer tracking","author":"Zhong","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0083","series-title":"Proc. IEEE\/CVF conf. comput. vis. pattern recognit. (CVPR)","first-page":"8761","article-title":"Global tracking via ensemble of local trackers","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neunet.2026.109052_bib0084","doi-asserted-by":"crossref","first-page":"4242","DOI":"10.1109\/TMM.2023.3321476","article-title":"Unit correlation with interactive feature for robust and effective tracking","volume":"26","author":"Zhou","year":"2023","journal-title":"IEEE Transactions on Multimedia. (TMM)"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005125?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005125?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:21:14Z","timestamp":1784200874000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026005125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":84,"alternative-id":["S0893608026005125"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109052","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Not all regions are equal: Spatially adaptive representation learning for efficient visual object tracking","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109052","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":"109052"}}