{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T03:34:42Z","timestamp":1794972882527,"version":"4.9.1"},"reference-count":54,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.neunet.2026.109322","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:37:13Z","timestamp":1782949033000},"page":"109322","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["Frequency-based cross-attention fusion network for RGB-D salient object detection"],"prefix":"10.1016","volume":"204","author":[{"given":"Xin","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyao","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109322_bib0001","series-title":"2009\u202fIEEE Conference on computer vision and pattern recognition","first-page":"1597","article-title":"Frequency-tuned salient region detection","author":"Achanta","year":"2009"},{"issue":"s1","key":"10.1016\/j.neunet.2026.109322_bib0002","doi-asserted-by":"crossref","first-page":"s77","DOI":"10.1515\/joc-2019-0116","article-title":"Signal processing criteria based on electro-optic filters for fiber optic access transceiver systems","volume":"45","author":"Amiri","year":"2025","journal-title":"Journal of Optical Communications"},{"key":"10.1016\/j.neunet.2026.109322_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109194","article-title":"Cross-modal hierarchical interaction network for RGB-d salient object detection","volume":"136","author":"Bi","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109322_bib0004","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1109\/TIP.2024.3364022","article-title":"Disentangled cross-modal transformer for RGB-d salient object detection and beyond","volume":"33","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109322_bib0005","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.neucom.2022.12.004","article-title":"Adaptive fusion network for RGB-d salient object detection","volume":"522","author":"Chen","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109322_bib0006","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10051","article-title":"Rest: A reconfigurable spatial-temporal graph model for multi-camera multi-object tracking","author":"Cheng","year":"2023"},{"key":"10.1016\/j.neunet.2026.109322_bib0007","doi-asserted-by":"crossref","first-page":"6800","DOI":"10.1109\/TIP.2022.3216198","article-title":"CIR-Net: Cross-modality interaction and refinement for RGB-D salient object detection","volume":"31","author":"Cong","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109322_bib0008","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"406","article-title":"Point-aware interaction and CNN-induced refinement network for RGB-D salient object detection","author":"Cong","year":"2023"},{"key":"10.1016\/j.neunet.2026.109322_bib0009","unstructured":"Diederik, P. K. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv: 1412.6980."},{"key":"10.1016\/j.neunet.2026.109322_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12124","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2022"},{"key":"10.1016\/j.neunet.2026.109322_bib0011","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.2026.109322_bib0012","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Gong, C., Cao, Y., Ren, B., Cheng, M.-M., & Borji, A. (2018). Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv: 1805.10421.","DOI":"10.24963\/ijcai.2018\/97"},{"issue":"5","key":"10.1016\/j.neunet.2026.109322_bib0013","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.1109\/TNNLS.2020.2996406","article-title":"Rethinking RGB-D salient object detection: Models, data sets, and large-scale benchmarks","volume":"32","author":"Fan","year":"2020","journal-title":"IEEE Transactions on neural networks and learning systems"},{"key":"10.1016\/j.neunet.2026.109322_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3052","article-title":"JL-DCF: Joint learning and densely-cooperative fusion framework for RGB-D salient object detection","author":"Fu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109322_bib0015","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109322_bib0016","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.1007\/s11263-024-02020-y","article-title":"Cross-modal fusion and progressive decoding network for RGB-D salient object detection","volume":"132","author":"Hu","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109322_bib0017","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, glasgow, UK, august 23\u201328, 2020, proceedings, part XVIII 16","first-page":"52","article-title":"Accurate RGB-D salient object detection via collaborative learning","author":"Ji","year":"2020"},{"key":"10.1016\/j.neunet.2026.109322_bib0018","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.neucom.2022.04.015","article-title":"FCMNet: Frequency-aware cross-modality attention networks for RGB-D salient object detection","volume":"491","author":"Jin","year":"2022","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109322_bib0019","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TCDS.2021.3135948","article-title":"Visual sentiment classification via low-rank regularization and label relaxation","volume":"14","author":"Jin","year":"2021","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"11","key":"10.1016\/j.neunet.2026.109322_bib0020","doi-asserted-by":"crossref","first-page":"7632","DOI":"10.1109\/TCSVT.2022.3180274","article-title":"MoADNet: Mobile asymmetric dual-stream networks for real-time and lightweight RGB-D salient object detection","volume":"32","author":"Jin","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109322_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129129","article-title":"DFD-NAS: General deepfake detection via efficient neural architecture search","volume":"619","author":"Jin","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109322_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128607","article-title":"Image manipulation localization via dynamic cross-modality fusion and progressive integration","volume":"610","author":"Jin","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109322_bib0023","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.2026.109322_bib0024","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1109\/TIP.2021.3062689","article-title":"Hierarchical alternate interaction network for RGB-D salient object detection","volume":"30","author":"Li","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109322_bib0025","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2806","article-title":"Saliency detection on light field","author":"Li","year":"2014"},{"issue":"3","key":"10.1016\/j.neunet.2026.109322_bib0026","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1007\/s11263-024-02245-x","article-title":"Unified frequency-assisted transformer framework for detecting and grounding multi-modal manipulation","volume":"133","author":"Liu","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109322_bib0027","article-title":"ColorSketchNet: Unifying color, sketch and texture for modality-agnostic multi-modal person re-identification","volume":"196","author":"Liu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109322_bib0028","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109322_bib0029","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.neucom.2019.07.012","article-title":"Salient object detection for RGB-D image by single stream recurrent convolution neural network","volume":"363","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109322_bib0030","series-title":"Proceedings of the 29th ACM international conference on multimedia","first-page":"4481","article-title":"TriTransNet: RGB-D salient object detection with a triplet transformer embedding network","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109322_bib0031","doi-asserted-by":"crossref","first-page":"4741","DOI":"10.1109\/TCE.2024.3390841","article-title":"Transformer-based cross-modal integration network for RGB-T salient object detection","volume":"70","author":"Lv","year":"2024","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.neunet.2026.109322_bib0032","article-title":"Hybrid aggregation strategy with double inverted residual blocks for lightweight salient object detection","volume":"194","author":"Ma","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109322_bib0033","series-title":"2012\u202fIEEE Conference on computer vision and pattern recognition","first-page":"454","article-title":"Leveraging stereopsis for saliency analysis","author":"Niu","year":"2012"},{"key":"10.1016\/j.neunet.2026.109322_bib0034","series-title":"Computer vision\u2013ECCV 2014: 13th european conference, zurich, switzerland, september 6\u201312, 2014, proceedings, part III 13","first-page":"92","article-title":"RGBD salient object detection: A benchmark and algorithms","author":"Peng","year":"2014"},{"key":"10.1016\/j.neunet.2026.109322_bib0035","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7254","article-title":"Depth-induced multi-scale recurrent attention network for saliency detection","author":"Piao","year":"2019"},{"key":"10.1016\/j.neunet.2026.109322_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106948","article-title":"TENet: Targetness entanglement incorporating with multi-scale pooling and mutually-guided fusion for RGB-E object tracking","volume":"183","author":"Shao","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109322_bib0037","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.1109\/TMM.2023.3294003","article-title":"CATNet: A cascaded and aggregated transformer network for RGB-D salient object detection","volume":"26","author":"Sun","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109322_bib0038","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3183","article-title":"Deep networks for saliency detection via local estimation and global search","author":"Wang","year":"2015"},{"issue":"3","key":"10.1016\/j.neunet.2026.109322_bib0039","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.2026.109322_bib0040","doi-asserted-by":"crossref","first-page":"2160","DOI":"10.1109\/TIP.2023.3263111","article-title":"HiDAnet: RGB-D salient object detection via hierarchical depth awareness","volume":"32","author":"Wu","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109322_bib0041","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"3455","article-title":"Object segmentation by mining cross-modal semantics","author":"Wu","year":"2023"},{"issue":"8","key":"10.1016\/j.neunet.2026.109322_bib0042","doi-asserted-by":"crossref","first-page":"5346","DOI":"10.1109\/TCSVT.2022.3144852","article-title":"Bi-directional progressive guidance network for RGB-D salient object detection","volume":"32","author":"Yang","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"9","key":"10.1016\/j.neunet.2026.109322_bib0043","first-page":"5761","article-title":"Uncertainty inspired RGB-D saliency detection","volume":"44","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109322_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8582","article-title":"UC-Net: Uncertainty inspired RGB-D saliency detection via conditional variational autoencoders","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109322_bib0045","doi-asserted-by":"crossref","first-page":"2477","DOI":"10.1109\/TMM.2024.3521699","article-title":"FasterSal: Robust and real-time single-stream architecture for RGB-D salient object detection","volume":"27","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109322_bib0046","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, glasgow, UK, august 23\u201328, 2020, proceedings, part XXII 16","first-page":"646","article-title":"A single stream network for robust and real-time RGB-D salient object detection","author":"Zhao","year":"2020"},{"key":"10.1016\/j.neunet.2026.109322_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110043","article-title":"Frequency-aware feature aggregation network with dual-task consistency for RGB-T salient object detection","volume":"146","author":"Zhou","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109322_bib0048","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4681","article-title":"Specificity-preserving RGB-D saliency detection","author":"Zhou","year":"2021"},{"issue":"6","key":"10.1016\/j.neunet.2026.109322_bib0049","doi-asserted-by":"crossref","first-page":"3641","DOI":"10.1109\/TSMC.2019.2957386","article-title":"Global and local-contrast guides content-aware fusion for RGB-D saliency prediction","volume":"51","author":"Zhou","year":"2019","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"10.1016\/j.neunet.2026.109322_bib0050","first-page":"1","article-title":"LLRailDet: Task-specific asymmetrical decoupling for robust low-light railway defect detection","volume":"75","author":"Zhou","year":"2026","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"4","key":"10.1016\/j.neunet.2026.109322_bib0051","doi-asserted-by":"crossref","DOI":"10.1142\/S0129065725500157","article-title":"Frequency-assisted local attention in lower layers of visual transformers","volume":"35","author":"Zhou","year":"2025","journal-title":"International Journal of Neural Systems"},{"key":"10.1016\/j.neunet.2026.109322_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113851","article-title":"ELAFormer: Early local attention in multi-scale vision transformers","volume":"325","author":"Zhou","year":"2025","journal-title":"Knowledge-Based Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.109322_bib0053","doi-asserted-by":"crossref","first-page":"8385","DOI":"10.1007\/s11063-023-11316-y","article-title":"Unsupervised saliency detection via knn mechanism and object-biased prior","volume":"55","author":"Zhou","year":"2023","journal-title":"Neural Processing Letters"},{"key":"10.1016\/j.neunet.2026.109322_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103039","article-title":"IFIFusion: A independent feature information fusion model for surface defect detection","volume":"120","author":"Zhou","year":"2025","journal-title":"Information Fusion"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007823?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007823?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:42:31Z","timestamp":1789083751000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026007823"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":54,"alternative-id":["S0893608026007823"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109322","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Frequency-based cross-attention fusion network for RGB-D salient object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109322","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109322"}}