{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:09:35Z","timestamp":1783350575751,"version":"3.54.6"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T00:00:00Z","timestamp":1734393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>RGB-T Salient Object Detection (SOD) aims to accurately segment salient regions in both visible light and thermal infrared images. However, many existing methods overlook the critical complementarity between these modalities, which can enhance detection accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We propose the Edge-Guided Feature Fusion Network (EGFF-Net), which consists of cross-modal feature extraction, edge-guided feature fusion, and salience map prediction. Firstly, the cross-modal feature extraction module captures and aggregates united and intersecting information in each local region of RGB and thermal images. Then, the edge-guided feature fusion module enhances the edge features of salient regions, considering that edge information is very helpful in refining significant area details. Moreover, a layer-by-layer decoding structure integrates multi-level features and generates the prediction of salience maps.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We conduct extensive experiments on three benchmark datasets and compare EGFF-Net with state-of-the-art methods. Our approach achieves superior performance, demonstrating the effectiveness of the proposed modules in improving both detection accuracy and boundary refinement.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The results highlight the importance of integrating cross-modal information and edge-guided fusion in RGB-T SOD. Our method outperforms existing techniques and provides a robust framework for future developments in multi-modal saliency detection.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2024.1489658","type":"journal-article","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T06:24:35Z","timestamp":1734416675000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Edge-guided feature fusion network for RGB-T salient object detection"],"prefix":"10.3389","volume":"18","author":[{"given":"Yuanlin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zengbao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,12,17]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"1597","DOI":"10.1109\/CVPR.2009.5206596","article-title":"\u201cFrequency-tuned salient region detection,\u201d","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Achanta","year":"2009"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05587","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.infrared.2018.05.006","article-title":"General fusion method for infrared and visual images via latent low-rank representation and local non-subsampled shearlet transform","volume":"92","author":"Cheng","year":"2018","journal-title":"Infrared Phys. Technol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"4819","DOI":"10.1109\/TIP.2019.2910377","article-title":"Video saliency detection via sparsity-based reconstruction and propagation","volume":"28","author":"Cong","year":"2019","journal-title":"IEEE Transact. Image Process"},{"key":"B5","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1109\/CISCE62493.2024.10653167","article-title":"\u201cRGB-T salient object detection based on the segment anything model,\u201d","volume-title":"2024 6th International Conference on Communications, Information System and Computer Engineering (CISCE)","author":"He","year":"2024"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1585","DOI":"10.1109\/LSP.2020.3020735","article-title":"RGB-T saliency detection via low-rank tensor learning and unified collaborative ranking","volume":"27","author":"Huang","year":"2020","journal-title":"IEEE Signal Process. Lett"},{"key":"B7","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/WACV.2018.00133","article-title":"\u201cSalient region-based online object tracking,\u201d","volume-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Lee","year":"2018"},{"key":"B8","doi-asserted-by":"publisher","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 Transact. Image Process"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1109\/TIP.2020.3044440","article-title":"Personal fixations-based object segmentation with object localization and boundary preservation","volume":"30","author":"Li","year":"2020","journal-title":"IEEE Transact. Image Process"},{"key":"B10","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.neucom.2019.08.051","article-title":"Constrained fixation point based segmentation via deep neural network","volume":"368","author":"Li","year":"2019","journal-title":"Neurocomputing"},{"key":"B11","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.1109\/TCSVT.2021.3127149","article-title":"Swinnet: swin transformer drives edge-aware RGB-D and RGB-T salient object detection","volume":"32","author":"Liu","year":"2022","journal-title":"IEEE Transact. Circ. Syst. Video Technol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"9496","DOI":"10.1109\/TIP.2020.3028170","article-title":"Boundary-aware rgbd salient object detection with cross-modal feature sampling","volume":"29","author":"Niu","year":"2020","journal-title":"IEEE Transact. Image Process"},{"key":"B13","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1109\/TIP.2023.3234702","article-title":"Caver: cross-modal view-mixed transformer for bi-modal salient object detection","volume":"32","author":"Pang","year":"2023","journal-title":"IEEE Transact. Image Process"},{"key":"B14","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1109\/CVPR.2012.6247743","article-title":"\u201cSaliency filters: contrast based filtering for salient region detection,\u201d","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","author":"Perazzi","year":"2012"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4421","DOI":"10.1109\/TCSVT.2019.2951621","article-title":"Rgbt salient object detection: benchmark and a novel cooperative ranking approach","volume":"30","author":"Tang","year":"2019","journal-title":"IEEE Transact. Circ. Syst. Video Technol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"5678","DOI":"10.1109\/TIP.2021.3087412","article-title":"Multi-interactive dual-decoder for RGB-thermal salient object detection","volume":"30","author":"Tu","year":"2021","journal-title":"IEEE Transact. Image Process"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3752","DOI":"10.1109\/TIP.2022.3176540","article-title":"Weakly alignment-free RGBT salient object detection with deep correlation network","volume":"31","author":"Tu","year":"2022","journal-title":"IEEE Transact. Image Process"},{"key":"B18","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/TMM.2019.2924578","article-title":"RGB-T image saliency detection via collaborative graph learning","volume":"22","author":"Tu","year":"2020","journal-title":"IEEE Transact. Multim"},{"key":"B19","doi-asserted-by":"publisher","first-page":"7942","DOI":"10.1080\/01431161.2018.1479791","article-title":"A novel remote-sensing image fusion method based on hybrid visual saliency analysis","volume":"39","author":"Zhang","year":"2018","journal-title":"Int. J. Remote Sens"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3321","DOI":"10.1109\/TIP.2019.2959253","article-title":"Rgb-t salient object detection via fusing multi-level cnn features","volume":"29","author":"Zhang","year":"2019","journal-title":"IEEE Transact. Image Process"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3027","DOI":"10.1109\/TIP.2023.3275538","article-title":"Wavenet: wavelet network with knowledge distillation for rgb-t salient object detection","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Transact. Image Process"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1489658\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T06:24:39Z","timestamp":1734416679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1489658\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,17]]},"references-count":21,"alternative-id":["10.3389\/fnbot.2024.1489658"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1489658","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,17]]},"article-number":"1489658"}}