{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:14:27Z","timestamp":1780402467667,"version":"3.54.1"},"reference-count":61,"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","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":[[2026,11]]},"DOI":"10.1016\/j.neunet.2026.109169","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:31:56Z","timestamp":1779899516000},"page":"109169","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A unified multi-stream diffusion framework for robust video camouflaged object detection"],"prefix":"10.1016","volume":"203","author":[{"given":"Yuyao","family":"Ke","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2734-915X","authenticated-orcid":false,"given":"Rui","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5294-7948","authenticated-orcid":false,"given":"Kunyang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hancheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109169_bib0001","series-title":"European conference on computer vision","first-page":"433","article-title":"It\u2019s moving! a probabilistic model for causal motion segmentation in moving camera videos","author":"Bideau","year":"2016"},{"key":"10.1016\/j.neunet.2026.109169_bib0002","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4175","article-title":"Denoising pretraining for semantic segmentation","author":"Brempong","year":"2022"},{"key":"10.1016\/j.neunet.2026.109169_bib0003","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"909","article-title":"A generalist framework for panoptic segmentation of images and videos","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109169_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5896","article-title":"Learning a sparse transformer network for effective image deraining","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109169_bib0005","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1272","article-title":"CamoDiffusion: Camouflaged object detection via conditional diffusion models","volume":"vol. 38","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13864","article-title":"Implicit motion handling for video camouflaged object detection","author":"Cheng","year":"2022"},{"issue":"9","key":"10.1016\/j.neunet.2026.109169_bib0007","doi-asserted-by":"crossref","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion models in vision: A survey","volume":"45","author":"Croitoru","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109169_bib0008","article-title":"Polyp-PVT: Polyp segmentation with pyramid vision transformers","volume":"2","author":"Dong","year":"2023","journal-title":"CAAI Artificial Intelligence Research"},{"key":"10.1016\/j.neunet.2026.109169_bib0009","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4548","article-title":"Structure-measure: A new way to evaluate foreground maps","author":"Fan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109169_bib0010","series-title":"Proceedings of the 27th international joint conference on artificial intelligence","first-page":"698","article-title":"Enhanced-alignment measure for binary foreground map evaluation","author":"Fan","year":"2018"},{"issue":"10","key":"10.1016\/j.neunet.2026.109169_bib0011","doi-asserted-by":"crossref","first-page":"6024","DOI":"10.1109\/TPAMI.2021.3085766","article-title":"Concealed object detection","volume":"44","author":"Fan","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109169_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2777","article-title":"Camouflaged object detection","author":"Fan","year":"2020"},{"key":"10.1016\/j.neunet.2026.109169_bib0013","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"263","article-title":"PraNet: Parallel reverse attention network for polyp segmentation","author":"Fan","year":"2020"},{"issue":"8","key":"10.1016\/j.neunet.2026.109169_bib0014","doi-asserted-by":"crossref","first-page":"2626","DOI":"10.1109\/TMI.2020.2996645","article-title":"Inf-Net: Automatic covid-19 lung infection segmentation from ct images","volume":"39","author":"Fan","year":"2020","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.neunet.2026.109169_bib0015","unstructured":"Gao, S., Feng, Y., Wang, Q., Hong, L., Zhou, X., Fei, L., Wang, Y., & Zhang, W. (2025). MSVCOD: A large-scale multi-scene dataset for video camouflage object detection. arXiv preprint arXiv:2502.13859."},{"issue":"1","key":"10.1016\/j.neunet.2026.109169_bib0016","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/0166-2236(92)90344-8","article-title":"Separate visual pathways for perception and action","volume":"15","author":"Goodale","year":"1992","journal-title":"Trends in Neurosciences"},{"issue":"6","key":"10.1016\/j.neunet.2026.109169_bib0017","doi-asserted-by":"crossref","first-page":"4630","DOI":"10.1109\/TPAMI.2025.3545047","article-title":"Diffusion models in low-level vision: A survey","volume":"47","author":"He","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109169_bib0018","doi-asserted-by":"crossref","first-page":"123453","DOI":"10.1109\/ACCESS.2019.2937461","article-title":"A fully convolutional neural network for wood defect location and identification","volume":"7","author":"He","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.109169_bib0019","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5557","article-title":"Feature shrinkage pyramid for camouflaged object detection with transformers","author":"Huang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109169_bib0020","doi-asserted-by":"crossref","first-page":"7188","DOI":"10.1109\/TMM.2024.3361170","article-title":"Implicit-explicit motion learning for video camouflaged object detection","volume":"26","author":"Hui","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109169_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19058","article-title":"Endow sam with keen eyes: Temporal-spatial prompt learning for video camouflaged object detection","author":"Hui","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0022","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"142","article-title":"Progressively normalized self-attention network for video polyp segmentation","author":"Ji","year":"2021"},{"issue":"1","key":"10.1016\/j.neunet.2026.109169_bib0023","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s11633-022-1365-9","article-title":"Deep gradient learning for efficient camouflaged object detection","volume":"20","author":"Ji","year":"2023","journal-title":"Machine Intelligence Research"},{"issue":"6","key":"10.1016\/j.neunet.2026.109169_bib0024","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/s11633-022-1371-y","article-title":"Video polyp segmentation: A deep learning perspective","volume":"19","author":"Ji","year":"2022","journal-title":"Machine Intelligence Research"},{"key":"10.1016\/j.neunet.2026.109169_bib0025","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"21741","article-title":"DDP: Diffusion model for dense visual prediction","author":"Ji","year":"2023"},{"key":"10.1016\/j.neunet.2026.109169_bib0026","doi-asserted-by":"crossref","first-page":"6647","DOI":"10.1109\/TIP.2024.3498331","article-title":"Transformer-based light field salient object detection and its application to autofocus","volume":"33","author":"Jiang","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109169_bib0027","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.neunet.2026.109169_bib0028","series-title":"Proceedings of the asian conference on computer vision","article-title":"Betrayed by motion: Camouflaged object discovery via motion segmentation","author":"Lamdouar","year":"2020"},{"issue":"12","key":"10.1016\/j.neunet.2026.109169_bib0029","doi-asserted-by":"crossref","first-page":"11990","DOI":"10.1109\/TPAMI.2025.3600461","article-title":"Towards real zero-shot camouflaged object segmentation without camouflaged annotations","volume":"47","author":"Lei","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109169_bib0030","series-title":"International conference on learning representations","article-title":"Omni-dimensional dynamic convolution","author":"Li","year":"2022"},{"issue":"12","key":"10.1016\/j.neunet.2026.109169_bib0031","doi-asserted-by":"crossref","first-page":"9909","DOI":"10.1109\/TIE.2019.2893843","article-title":"Concealed object detection for activate millimeter wave image","volume":"66","author":"Liu","year":"2019","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"10.1016\/j.neunet.2026.109169_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11591","article-title":"Simultaneously localize, segment and rank the camouflaged objects","author":"Lv","year":"2021"},{"key":"10.1016\/j.neunet.2026.109169_bib0033","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"How to evaluate foreground maps?","author":"Margolin","year":"2014"},{"issue":"4","key":"10.1016\/j.neunet.2026.109169_bib0034","doi-asserted-by":"crossref","first-page":"152","DOI":"10.5539\/mas.v5n4p152","article-title":"Study on the camouflaged target detection method based on 3d convexity","volume":"5","author":"Pan","year":"2011","journal-title":"Modern Applied Science"},{"key":"10.1016\/j.neunet.2026.109169_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2160","article-title":"Zoom in and out: A mixed-scale triplet network for camouflaged object detection","author":"Pang","year":"2022"},{"issue":"12","key":"10.1016\/j.neunet.2026.109169_bib0036","doi-asserted-by":"crossref","first-page":"9205","DOI":"10.1109\/TPAMI.2024.3417329","article-title":"ZoomNeXt: A unified collaborative pyramid network for camouflaged object detection","volume":"46","author":"Pang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109169_bib0037","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"117","article-title":"CleanDIFT: Diffusion features without noise","author":"Stracke","year":"2025"},{"issue":"4","key":"10.1016\/j.neunet.2026.109169_bib0038","doi-asserted-by":"crossref","first-page":"2833","DOI":"10.1109\/TPAMI.2025.3527469","article-title":"Conditional diffusion models for camouflaged and salient object detection","volume":"47","author":"Sun","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109169_bib0039","series-title":"31st international joint conference on artificial intelligence, IJCAI 2022","first-page":"1335","article-title":"Boundary-guided camouflaged object detection","author":"Sun","year":"2022"},{"key":"10.1016\/j.neunet.2026.109169_bib0040","series-title":"European conference on computer vision","first-page":"343","article-title":"Frequency-spatial entanglement learning for camouflaged object detection","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0041","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"8805","article-title":"Chain of visual perception: Harnessing multimodal large language models for zero-shot camouflaged object detection","author":"Tang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106751","article-title":"DmgNet: Depth mask guiding network for rgb-d salient object detection","volume":"180","author":"Tang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109169_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107915","article-title":"Long-range diffusion for weakly camouflaged object segmentation","volume":"192","author":"Wang","year":"2025","journal-title":"Neural Networks"},{"issue":"3","key":"10.1016\/j.neunet.2026.109169_bib0044","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"PVT v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Computational Visual Media"},{"key":"10.1016\/j.neunet.2026.109169_bib0045","series-title":"International conference on medical imaging with deep learning","first-page":"1336","article-title":"Diffusion models for implicit image segmentation ensembles","author":"Wolleb","year":"2022"},{"key":"10.1016\/j.neunet.2026.109169_bib0046","series-title":"Medical imaging with deep learning","first-page":"1623","article-title":"MedSegDiff: Medical image segmentation with diffusion probabilistic model","author":"Wu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0047","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"6030","article-title":"MedSegDiff-v2: Diffusion-based medical image segmentation with transformer","volume":"vol. 38","author":"Wu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0048","article-title":"Disentangled self-supervised video camouflaged object detection and salient object detection","volume":"194","author":"Xiao","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109169_bib0049","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9994","article-title":"Object discovery in videos as foreground motion clustering","author":"Xie","year":"2019"},{"key":"10.1016\/j.neunet.2026.109169_bib0050","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7284","article-title":"Semi-supervised video salient object detection using pseudo-labels","author":"Yan","year":"2019"},{"key":"10.1016\/j.neunet.2026.109169_bib0051","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7177","article-title":"Self-supervised video object segmentation by motion grouping","author":"Yang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109169_bib0052","doi-asserted-by":"crossref","first-page":"5936","DOI":"10.1109\/TIP.2024.3475219","article-title":"Hierarchical graph interaction transformer with dynamic token clustering for camouflaged object detection","volume":"33","author":"Yao","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109169_bib0053","series-title":"ICASSP 2024-2024 IEEE International conference on acoustics, speech and signal processing (ICASSP)","first-page":"2875","article-title":"TokenMotion: Motion-guided vision transformer for video camouflaged object detection via learnable token selection","author":"Yu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0054","first-page":"1","article-title":"A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection","volume":"71","author":"Zeng","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2026.109169_bib0055","series-title":"ICASSP 2022-2022 Ieee international conference on acoustics, speech and signal processing (ICASSP)","first-page":"3803","article-title":"FdsNet: An accurate real-time surface defect segmentation network","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109169_bib0056","doi-asserted-by":"crossref","first-page":"2853","DOI":"10.1109\/TIP.2025.3565879","article-title":"Explicit motion handling and interactive prompting for video camouflaged object detection","volume":"634","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109169_bib0057","doi-asserted-by":"crossref","first-page":"3580","DOI":"10.1109\/TIP.2023.3287137","article-title":"Predictive uncertainty estimation for camouflaged object detection","volume":"32","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109169_bib0058","series-title":"European conference on computer vision","first-page":"181","article-title":"FocusDiffuser: Perceiving local disparities for camouflaged object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109169_bib0059","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"120","article-title":"Automatic polyp segmentation via multi-scale subtraction network","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109169_bib0060","series-title":"International symposium on photoelectronic detection and imaging 2013: Imaging sensors and applications","first-page":"376","article-title":"Camouflaged target separation by spectral-polarimetric imagery fusion with shearlet transform and clustering segmentation","volume":"vol. 8908","author":"Zhou","year":"2013"},{"key":"10.1016\/j.neunet.2026.109169_bib0061","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","article-title":"Deformable convnets v2: More deformable, better results","author":"Zhu","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006301?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006301?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:57:41Z","timestamp":1780401461000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026006301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":61,"alternative-id":["S0893608026006301"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109169","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A unified multi-stream diffusion framework for robust video camouflaged object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109169","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":"109169"}}