{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:10:38Z","timestamp":1776100238293,"version":"3.50.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2023YFD2401104"],"award-info":[{"award-number":["2023YFD2401104"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2019MEE019"],"award-info":[{"award-number":["ZR2019MEE019"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2020ME112"],"award-info":[{"award-number":["ZR2020ME112"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009108","name":"Shandong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2024A1515011555"],"award-info":[{"award-number":["2024A1515011555"]}],"id":[{"id":"10.13039\/501100003453","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":[[2026,6]]},"DOI":"10.1016\/j.neunet.2026.108705","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:42:41Z","timestamp":1770741761000},"page":"108705","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TransUTD: Underwater cross-domain collaborative spatial-temporal transformer detector"],"prefix":"10.1016","volume":"198","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8331-1430","authenticated-orcid":false,"given":"Bingxun","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6264-1972","authenticated-orcid":false,"given":"Xiao","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1736-9604","authenticated-orcid":false,"given":"Ruihao","family":"Sui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1611-1023","authenticated-orcid":false,"given":"Yuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108705_bib0001","series-title":"European conference on computer vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neunet.2026.108705_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106809","article-title":"Rectangling and enhancing underwater stitched image via content-aware warping and perception balancing","volume":"181","author":"Chang","year":"2025","journal-title":"Neural Networks"},{"issue":"7","key":"10.1016\/j.neunet.2026.108705_bib0003","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s10462-024-10788-1","article-title":"Dynamic YOLO for small underwater object detection","volume":"57","author":"Chen","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.neunet.2026.108705_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108926","article-title":"SWIPENET: Object detection in noisy underwater scenes","volume":"132","author":"Chen","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108705_bib0005","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.neunet.2021.08.014","article-title":"One-stage CNN detector-based benthonic organisms detection with limited training dataset","volume":"144","author":"Chen","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108705_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10337","article-title":"Memory enhanced global-local aggregation for video object detection","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.108705_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110222","article-title":"A gated cross-domain collaborative network for underwater object detection","volume":"149","author":"Dai","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108705_bib0008","series-title":"2019 IEEE\/CVF international conference on computer vision (iccv)","first-page":"7022","article-title":"Relation distillation networks for video object detection","author":"Deng","year":"2019"},{"key":"10.1016\/j.neunet.2026.108705_bib0009","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2758","article-title":"Flownet: Learning optical flow with convolutional networks","author":"Dosovitskiy","year":"2015"},{"key":"10.1016\/j.neunet.2026.108705_bib0010","series-title":"European conference on computer vision","first-page":"275","article-title":"Dual refinement underwater object detection network","author":"Fan","year":"2020"},{"key":"10.1016\/j.neunet.2026.108705_bib0011","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.neucom.2022.10.039","article-title":"Rethinking general underwater object detection: datasets, challenges, and solutions","volume":"517","author":"Fu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108705_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121688","article-title":"Augmented weighted bidirectional feature pyramid network for marine object detection","volume":"237","author":"Gao","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.1016\/j.neunet.2026.108705_bib0013","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1609\/aaai.v36i1.19965","article-title":"Queryprop: Object query propagation for high-performance video object detection","volume":"36","author":"He","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108705_bib0014","series-title":"European conference on computer vision","first-page":"89","article-title":"Relation DETR: Exploring explicit position relation prior for object detection","author":"Hou","year":"2025"},{"key":"10.1016\/j.neunet.2026.108705_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107568","article-title":"Fast underwater scene reconstruction using multi-view stereo and physical imaging","author":"Hu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108705_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109511","article-title":"Underwater object detection algorithm based on feature enhancement and progressive dynamic aggregation strategy","volume":"139","author":"Hua","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108705_bib0017","doi-asserted-by":"crossref","DOI":"10.1109\/TIP.2025.3609185","article-title":"Dual-view alignment learning with hierarchical-prompt for class-imbalance multi-label image classification","author":"Huang","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108705_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19702","article-title":"DETRs With hybrid matching","author":"Jia","year":"2023"},{"key":"10.1016\/j.neunet.2026.108705_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108323","article-title":"Feature flow: in-network feature flow estimation for video object detection","volume":"122","author":"Jin","year":"2022","journal-title":"Pattern Recognition"},{"issue":"4","key":"10.1016\/j.neunet.2026.108705_bib0020","doi-asserted-by":"crossref","first-page":"2239","DOI":"10.1109\/TPAMI.2023.3335410","article-title":"DN-DETR: Accelerate DETR training by introducing query denoising","volume":"46","author":"Li","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108705_bib0021","series-title":"2021 IEEE International conference on multimedia & expo workshops (icmew)","first-page":"1","article-title":"A dataset and benchmark of underwater object detection for robot picking","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108705_bib0022","doi-asserted-by":"crossref","first-page":"4922","DOI":"10.1109\/TIP.2022.3190209","article-title":"Twin adversarial contrastive learning for underwater image enhancement and beyond","volume":"31","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108705_bib0023","doi-asserted-by":"crossref","first-page":"2560","DOI":"10.1109\/TMM.2023.3301226","article-title":"Uiqi: A comprehensive quality evaluation index for underwater images","volume":"26","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.108705_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110435","article-title":"Unitmodule: A lightweight joint image enhancement module for underwater object detectionunitmodule","volume":"151","author":"Liu","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108705_bib0025","doi-asserted-by":"crossref","first-page":"3066","DOI":"10.1109\/TIP.2023.3276332","article-title":"U-Shape transformer for underwater image enhancement","volume":"32","author":"Peng","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"issue":"9","key":"10.1016\/j.neunet.2026.108705_bib0026","doi-asserted-by":"crossref","first-page":"5712","DOI":"10.1109\/TII.2019.2937902","article-title":"Walsh\u2013hadamard-kernel-based features in particle filter framework for underwater object tracking","volume":"16","author":"Rout","year":"2019","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"3","key":"10.1016\/j.neunet.2026.108705_bib0027","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108705_bib0028","doi-asserted-by":"crossref","unstructured":"Sabater, A., Montesano, L., & Murillo, A. C.. Robust and efficient post-processing for video object detection. in 2020\u202fIEEE. In Rsj international conference on intelligent robots and systems (iros) (pp. 10536\u201310542).","DOI":"10.1109\/IROS45743.2020.9341600"},{"key":"10.1016\/j.neunet.2026.108705_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111198","article-title":"Frequency domain-based latent diffusion model for underwater image enhancement","volume":"160","author":"Song","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108705_bib0030","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.neucom.2023.01.088","article-title":"Boosting R-CNN: Reweighting R-CNN samples by RPN\u2019s error for underwater object detection","volume":"530","author":"Song","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108705_bib0031","doi-asserted-by":"crossref","first-page":"2454","DOI":"10.1109\/TIP.2023.3268561","article-title":"Neural attention-driven non-maximum suppression for person detection","volume":"32","author":"Symeonidis","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.108705_bib0032","series-title":"International conference on multimedia modeling","first-page":"539","article-title":"Marine video kit: A new marine video dataset for content-based analysis and retrieval","author":"Truong","year":"2023"},{"key":"10.1016\/j.neunet.2026.108705_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111672","article-title":"A dual-branch joint learning network for underwater object detection","volume":"293","author":"Wang","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108705_bib0034","series-title":"European conference on computer vision","first-page":"732","article-title":"PTSEFormer: Progressive temporal-spatial enhanced transformer towards video object detection","author":"Wang","year":"2022"},{"issue":"1","key":"10.1016\/j.neunet.2026.108705_bib0035","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/TIE.2023.3247737","article-title":"Automatic seabed target segmentation of AUV via multilevel adversarial network and marginal distribution adaptation","volume":"71","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"2","key":"10.1016\/j.neunet.2026.108705_bib0036","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1109\/JOE.2023.3302888","article-title":"Is underwater image enhancement all object detectors need?","volume":"49","author":"Wang","year":"2024","journal-title":"IEEE Journal of Oceanic Engineering"},{"key":"10.1016\/j.neunet.2026.108705_bib0037","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1109\/TIP.2023.3244647","article-title":"Domain adaptation for underwater image enhancement","volume":"32","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"10.1016\/j.neunet.2026.108705_bib0038","doi-asserted-by":"crossref","first-page":"10743","DOI":"10.1109\/TCSVT.2024.3417000","article-title":"FIOD-VUE: Focusing on invariant information in object detection of varying underwater environment","volume":"34","author":"Xie","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"11","key":"10.1016\/j.neunet.2026.108705_bib0039","doi-asserted-by":"crossref","first-page":"6129","DOI":"10.1109\/TNNLS.2021.3072414","article-title":"Lightweight deep neural network for joint learning of underwater object detection and color conversion","volume":"33","author":"Yeh","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"7","key":"10.1016\/j.neunet.2026.108705_bib0040","doi-asserted-by":"crossref","first-page":"9215","DOI":"10.1109\/TII.2024.3383537","article-title":"A novel underwater detection method for ambiguous object finding via distraction mining","volume":"20","author":"Yuan","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2026.108705_bib0041","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1016\/j.neunet.2023.11.008","article-title":"Robust underwater image enhancement with cascaded multi-level sub-networks and triple attention mechanism","volume":"169","author":"Zhang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108705_bib0042","series-title":"The eleventh international conference on learning representations","article-title":"DINO: DETR With improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108705_bib0043","article-title":"Cidnet: Cross-scale interference mining detection network for underwater object detection","author":"Zhao","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108705_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16965","article-title":"DETRs Beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.108705_bib0045","article-title":"Spatial residual for underwater object detection","author":"Zhou","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108705_bib0046","first-page":"1","article-title":"Underwater camera: Improving visual perception via adaptive dark pixel prior and color correction","author":"Zhou","year":"2023","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108705_bib0047","article-title":"Noise-aware state-space method for underwater object detection","author":"Zhou","year":"2025","journal-title":"Pattern Recognition"},{"issue":"6","key":"10.1016\/j.neunet.2026.108705_bib0048","doi-asserted-by":"crossref","first-page":"7853","DOI":"10.1109\/TPAMI.2022.3223955","article-title":"TransVOD: end-to-End video object detection with spatial-Temporal transformers","volume":"45","author":"Zhou","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108705_bib0049","series-title":"International conference on learning representations","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108705_bib0050","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"408","article-title":"Flow-guided feature aggregation for video object detection","author":"Zhu","year":"2017"},{"key":"10.1016\/j.neunet.2026.108705_bib0051","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2349","article-title":"Deep feature flow for video recognition","author":"Zhu","year":"2017"},{"key":"10.1016\/j.neunet.2026.108705_bib0052","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6748","article-title":"DETRs With collaborative hybrid assignments training","author":"Zong","year":"2023"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600167X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600167X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:11:44Z","timestamp":1776096704000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802600167X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":52,"alternative-id":["S089360802600167X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108705","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TransUTD: Underwater cross-domain collaborative spatial-temporal transformer detector","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108705","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":"108705"}}