{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:10:25Z","timestamp":1780495825265,"version":"3.54.1"},"reference-count":32,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["62162065"],"award-info":[{"award-number":["62162065"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113487","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:20:30Z","timestamp":1773825630000},"page":"113487","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["UWRGBD1k: A large-scale RGBD dataset of underwater object tracking"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6441-3352","authenticated-orcid":false,"given":"Kaixiang","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2895-2121","authenticated-orcid":false,"given":"Wenhua","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8562-5964","authenticated-orcid":false,"given":"Cong","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3283-454X","authenticated-orcid":false,"given":"Peng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113487_bib0001","series-title":"2019 IEEE International Symposium on Technologies for Homeland Security (HST)","first-page":"1","article-title":"Underwater object tracking benchmark and dataset","author":"Kezebou","year":"2019"},{"key":"10.1016\/j.patcog.2026.113487_bib0002","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"3326","article-title":"Utb180: a high-quality benchmark for underwater tracking","author":"Alawode","year":"2022"},{"key":"10.1016\/j.patcog.2026.113487_bib0003","unstructured":"B. Alawode, F.A. Dharejo, M. Ummar, Y. Guo, A. Mahmood, N. Werghi, F.S. Khan, J. Matas, S. Javed, Improving underwater visual tracking with a large scale dataset and image enhancement, (2023). arXiv: 2308.15816."},{"key":"10.1016\/j.patcog.2026.113487_bib0004","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"961","article-title":"A unified image-dense annotation generation model for underwater scenes","volume":"12","author":"Lin","year":"2025"},{"key":"10.1016\/j.patcog.2026.113487_bib0005","series-title":"Advances in Neural Information Processing Systems","first-page":"871","article-title":"NAUTILUS: a large multimodal model for underwater scene understanding","volume":"17","author":"Xu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113487_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111053","article-title":"Temporal adaptive bidirectional bridging for RGB-D tracking","volume":"158","author":"Ying","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113487_bib0007","doi-asserted-by":"crossref","first-page":"110543","DOI":"10.1016\/j.patcog.2024.110543","article-title":"Self-supervised learning for RGB-D object tracking","volume":"155","author":"Zhu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113487_bib0008","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"233","article-title":"Tracking revisited using RGBD camera: unified benchmark and baselines","author":"Song","year":"2013"},{"key":"10.1016\/j.patcog.2026.113487_bib0009","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10725","article-title":"Depthtrack: unveiling the power of rgbd tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.patcog.2026.113487_bib0010","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10013","article-title":"CDTB: a color and depth visual object tracking dataset and benchmark","author":"Lukezic","year":"2019"},{"issue":"1","key":"10.1016\/j.patcog.2026.113487_bib0011","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/JOE.2021.3086907","article-title":"Comprehensive underwater object tracking benchmark dataset and underwater image enhancement with GAN","volume":"47","author":"Panetta","year":"2021","journal-title":"IEEE J. Oceanic Eng."},{"key":"10.1016\/j.patcog.2026.113487_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22358","article-title":"UVEB: a large-scale benchmark and baseline towards real-world underwater video enhancement","author":"Xie","year":"2024"},{"key":"10.1016\/j.patcog.2026.113487_bib0013","first-page":"50152","article-title":"WebUOT-1M: advancing deep underwater object tracking with a million-scale benchmark","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.patcog.2026.113487_bib0014","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1109\/TCYB.2017.2740952","article-title":"Robust fusion of color and depth data for RGB-D target tracking using adaptive range-invariant depth models and spatio-temporal consistency constraints","volume":"48","author":"Xiao","year":"2017","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2026.113487_bib0015","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3870","article-title":"RGBD1K: a large-scale dataset and benchmark for RGB-D object tracking","volume":"37","author":"Zhu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113487_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3289","article-title":"Digital twin tracking dataset (DTTD): a new RGB+ depth 3D dataset for longer-range object tracking applications","author":"Feng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113487_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5126","article-title":"ARKitTrack: a new diverse dataset for tracking using mobile RGB-D data","author":"Zhao","year":"2023"},{"issue":"3","key":"10.1016\/j.patcog.2026.113487_bib0018","doi-asserted-by":"crossref","first-page":"2260","DOI":"10.1109\/TCSVT.2024.3497214","article-title":"RGB-sonar tracking benchmark and spatial cross-attention transformer tracker","volume":"35","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113487_bib0019","doi-asserted-by":"crossref","first-page":"6501","DOI":"10.1016\/j.oceaneng.2025.123224","article-title":"United-modality underwater object tracking via distinct enhancing and high-dimensional fusion","volume":"343","author":"Yan","year":"2026","journal-title":"Ocean Eng."},{"key":"10.1016\/j.patcog.2026.113487_bib0020","series-title":"ECCV","first-page":"6226","article-title":"Joint feature learning and relation modeling for tracking: a one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.patcog.2026.113487_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7136","article-title":"Correlation-aware deep tracking","author":"Xie","year":"2022"},{"key":"10.1016\/j.patcog.2026.113487_bib0022","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"6708","article-title":"Separable self and mixed attention transformers for efficient object tracking","author":"Gopal","year":"2024"},{"key":"10.1016\/j.patcog.2026.113487_bib0023","doi-asserted-by":"crossref","first-page":"115449","DOI":"10.1016\/j.oceaneng.2023.115449","article-title":"Underwater object tracker: UOSTrack for marine organism grasping of underwater vehicles","volume":"285","author":"Li","year":"2023","journal-title":"Ocean Eng."},{"issue":"3","key":"10.1016\/j.patcog.2026.113487_bib0024","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1109\/TSP.2024.3510755","article-title":"UncTrack: reliable visual object tracking with an uncertainty-aware prototype memory network","volume":"12","author":"Yao","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"10.1016\/j.patcog.2026.113487_bib0025","first-page":"72","article-title":"PUTrack: improved underwater object tracking via progressive prompting","volume":"22","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.patcog.2026.113487_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13630","article-title":"Bridging search region interaction with template for RGB-T tracking","author":"Hui","year":"2023"},{"key":"10.1016\/j.patcog.2026.113487_bib0027","series-title":"CVPR","first-page":"24630","article-title":"Visual prompt multi-Modal tracking","author":"Jiawen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113487_bib0028","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"927","article-title":"Bi-directional adapter for multimodal tracking","volume":"38","author":"Cao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113487_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"26551","article-title":"SDSTrack: self-distillation symmetric adapter learning for multi-modal visual object tracking","author":"Hou","year":"2024"},{"key":"10.1016\/j.patcog.2026.113487_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19156","article-title":"Single-model and any-modality for video object tracking","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113487_bib0031","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2239","article-title":"SUTrack: towards simple and unified single object tracking","volume":"39","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.113487_bib0032","series-title":"AAAI Conference on Artificial Intelligence","first-page":"32430","article-title":"Cross-modulated attention transformer for RGBT tracking","author":"Xiao","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600453X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600453X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:11:07Z","timestamp":1780492267000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032600453X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":32,"alternative-id":["S003132032600453X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113487","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"UWRGBD1k: A large-scale RGBD dataset of underwater object tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113487","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":"113487"}}