{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:25:07Z","timestamp":1783113907234,"version":"3.54.6"},"reference-count":44,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62350710796"],"award-info":[{"award-number":["62350710796"]}],"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":["62331024"],"award-info":[{"award-number":["62331024"]}],"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":["62371123"],"award-info":[{"award-number":["62371123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015013","name":"National Mobile Communications Research Laboratory, Southeast University","doi-asserted-by":"publisher","award":["2025A03"],"award-info":[{"award-number":["2025A03"]}],"id":[{"id":"10.13039\/501100015013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114155","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T23:43:33Z","timestamp":1780616613000},"page":"114155","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Occlusion-aware visual object tracking with explicit temporal state modeling and dual-memory mechanism"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4176-6381","authenticated-orcid":false,"given":"Zhipeng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linning","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijin","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun-Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114155_b1","series-title":"2015 International Conference on Pervasive Computing","first-page":"1","article-title":"Image processing techniques for object tracking in video surveillance-A survey","author":"Ojha","year":"2015"},{"key":"10.1016\/j.patcog.2026.114155_b2","series-title":"2017 22nd International Conference on Methods and Models in Automation and Robotics","first-page":"734","article-title":"Autonomous drone control system for object tracking: Flexible system design with implementation example","author":"Smyczy\u0144ski","year":"2017"},{"issue":"3","key":"10.1016\/j.patcog.2026.114155_b3","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.imavis.2012.01.003","article-title":"3D hand tracking for human computer interaction","volume":"30","author":"Prisacariu","year":"2012","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.patcog.2026.114155_b4","series-title":"European Conference on Computer Vision","first-page":"299","article-title":"Hard occlusions in visual object tracking","author":"Kuipers","year":"2020"},{"key":"10.1016\/j.patcog.2026.114155_b5","doi-asserted-by":"crossref","unstructured":"G. Sahin, L. Itti, HOOT: Heavy occlusions in object tracking benchmark, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 4830\u20134839.","DOI":"10.1109\/WACV56688.2023.00481"},{"key":"10.1016\/j.patcog.2026.114155_b6","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2023.1323188","article-title":"Target-aware transformer tracking with hard occlusion instance generation","volume":"17","author":"Xiao","year":"2024","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.patcog.2026.114155_b7","doi-asserted-by":"crossref","unstructured":"Y. Wu, X. Wang, X. Yang, M. Liu, D. Zeng, H. Ye, S. Li, Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 17103\u201317113.","DOI":"10.1109\/CVPR52734.2025.01594"},{"key":"10.1016\/j.patcog.2026.114155_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104440","article-title":"Occlusion-aware visual object tracking based on multi-template updating siamese network","volume":"148","author":"Sun","year":"2024","journal-title":"Digit. Signal Process."},{"issue":"24","key":"10.1016\/j.patcog.2026.114155_b9","doi-asserted-by":"crossref","first-page":"13045","DOI":"10.3390\/app152413045","article-title":"Towards occlusion-aware multi-pedestrian tracking","volume":"15","author":"Wang","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.patcog.2026.114155_b10","series-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"10.1016\/j.patcog.2026.114155_b11","series-title":"Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114155_b12","doi-asserted-by":"crossref","unstructured":"J. Videnovic, A. Lukezic, M. Kristan, A distractor-aware memory for visual object tracking with sam2, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 24255\u201324264.","DOI":"10.1109\/CVPR52734.2025.02259"},{"key":"10.1016\/j.patcog.2026.114155_b13","series-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"issue":"11","key":"10.1016\/j.patcog.2026.114155_b14","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114155_b15","doi-asserted-by":"crossref","unstructured":"M. Mueller, N.G. Smith, B. Ghanem, A Benchmark and Simulator for UAV Tracking, in: European Conference on Computer Vision, 2016.","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"10.1016\/j.patcog.2026.114155_b16","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Visual object tracking for unmanned aerial vehicles: A benchmark and new motion models","volume":"vol. 31","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2026.114155_b17","first-page":"1","article-title":"Onboard real-time aerial tracking with efficient siamese anchor proposal network","volume":"60","author":"Fu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"10.1016\/j.patcog.2026.114155_b18","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","article-title":"High-speed tracking with kernelized correlation filters","volume":"37","author":"Henriques","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114155_b19","doi-asserted-by":"crossref","unstructured":"M. Danelljan, G. Bhat, F. Shahbaz Khan, M. Felsberg, Eco: Efficient convolution operators for tracking, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6638\u20136646.","DOI":"10.1109\/CVPR.2017.733"},{"key":"10.1016\/j.patcog.2026.114155_b20","series-title":"European Conference on Computer Vision","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.patcog.2026.114155_b21","doi-asserted-by":"crossref","unstructured":"B. Li, J. Yan, W. Wu, Z. Zhu, X. Hu, High performance visual tracking with siamese region proposal network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8971\u20138980.","DOI":"10.1109\/CVPR.2018.00935"},{"key":"10.1016\/j.patcog.2026.114155_b22","doi-asserted-by":"crossref","unstructured":"B. Li, W. Wu, Q. Wang, F. Zhang, J. Xing, J. Yan, Siamrpn++: Evolution of siamese visual tracking with very deep networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4282\u20134291.","DOI":"10.1109\/CVPR.2019.00441"},{"key":"10.1016\/j.patcog.2026.114155_b23","doi-asserted-by":"crossref","unstructured":"X. Chen, B. Yan, J. Zhu, D. Wang, X. Yang, H. Lu, Transformer tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8126\u20138135.","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10.1016\/j.patcog.2026.114155_b24","series-title":"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"},{"issue":"3","key":"10.1016\/j.patcog.2026.114155_b25","first-page":"3072","article-title":"SiamMask: A framework for fast online object tracking and segmentation","volume":"45","author":"Wu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114155_b26","series-title":"European Conference on Computer Vision","first-page":"640","article-title":"Xmem: Long-term video object segmentation with an atkinson-shiffrin memory model","author":"Cheng","year":"2022"},{"key":"10.1016\/j.patcog.2026.114155_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128715","article-title":"MSAF: Multi-scale adaptive filter for object tracking","volume":"294","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114155_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107314","article-title":"A spatial\u2013temporal contexts network for object tracking","volume":"127","author":"Huang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114155_b29","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, et al., Segment anything, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.patcog.2026.114155_b30","doi-asserted-by":"crossref","unstructured":"S. Ding, R. Qian, X. Dong, P. Zhang, Y. Zang, Y. Cao, Y. Guo, D. Lin, J. Wang, Sam2long: Enhancing sam 2 for long video segmentation with a training-free memory tree, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 13614\u201313624.","DOI":"10.1109\/ICCV51701.2025.01264"},{"key":"10.1016\/j.patcog.2026.114155_b31","doi-asserted-by":"crossref","unstructured":"H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, H. Ling, Lasot: A high-quality benchmark for large-scale single object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5374\u20135383.","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"2","key":"10.1016\/j.patcog.2026.114155_b32","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":"Int. J. Comput. Vis."},{"issue":"5","key":"10.1016\/j.patcog.2026.114155_b33","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 Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114155_b34","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.patcog.2026.114155_b35","doi-asserted-by":"crossref","unstructured":"X. Chen, H. Peng, D. Wang, H. Lu, H. Hu, Seqtrack: Sequence to sequence learning for visual object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14572\u201314581.","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"10.1016\/j.patcog.2026.114155_b36","doi-asserted-by":"crossref","unstructured":"H.K. Cheng, S.W. Oh, B. Price, J.-Y. Lee, A. Schwing, Putting the object back into video object segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3151\u20133161.","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"10.1016\/j.patcog.2026.114155_b37","doi-asserted-by":"crossref","unstructured":"Y. Cui, C. Jiang, L. Wang, G. Wu, Mixformer: End-to-end tracking with iterative mixed attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13608\u201313618.","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"10.1016\/j.patcog.2026.114155_b38","series-title":"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.patcog.2026.114155_b39","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3991","article-title":"Diffusiontrack: Diffusion model for multi-object tracking","volume":"vol. 38","author":"Luo","year":"2024"},{"key":"10.1016\/j.patcog.2026.114155_b40","doi-asserted-by":"crossref","unstructured":"Q. Wu, T. Yang, Z. Liu, B. Wu, Y. Shan, A.B. Chan, Dropmae: Masked autoencoders with spatial-attention dropout for tracking tasks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14561\u201314571.","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"10.1016\/j.patcog.2026.114155_b41","doi-asserted-by":"crossref","unstructured":"S. Gao, C. Zhou, J. Zhang, Generalized relation modeling for transformer tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18686\u201318695.","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"10.1016\/j.patcog.2026.114155_b42","doi-asserted-by":"crossref","unstructured":"Y. Cai, J. Liu, J. Tang, G. Wu, Robust object modeling for visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 9589\u20139600.","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"10.1016\/j.patcog.2026.114155_b43","doi-asserted-by":"crossref","unstructured":"C. Mayer, M. Danelljan, D.P. Paudel, L. Van Gool, Learning target candidate association to keep track of what not to track, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13444\u201313454.","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"10.1016\/j.patcog.2026.114155_b44","doi-asserted-by":"crossref","unstructured":"C. Mayer, M. Danelljan, G. Bhat, M. Paul, D.P. Paudel, F. Yu, L. Van Gool, Transforming model prediction for tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8731\u20138740.","DOI":"10.1109\/CVPR52688.2022.00853"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011209?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011209?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:12:03Z","timestamp":1783113123000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326011209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":44,"alternative-id":["S0031320326011209"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114155","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Occlusion-aware visual object tracking with explicit temporal state modeling and dual-memory mechanism","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114155","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":"114155"}}