{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T06:39:08Z","timestamp":1776926348145,"version":"3.51.2"},"reference-count":60,"publisher":"Tech Science Press","issue":"3","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"vor","delay-in-days":214,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.066188","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T03:54:28Z","timestamp":1751601268000},"page":"5613-5635","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["MGD-YOLO: An Enhanced Road Defect Detection Algorithm Based on Multi-Scale Attention Feature Fusion"],"prefix":"10.32604","volume":"84","author":[{"given":"Zhengji","family":"Li","sequence":"first","affiliation":[]},{"given":"Fazhan","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Boyun","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Meihui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Yingrui","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Jiacheng","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Aokun","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","article-title":"A computational approach to edge detection","volume":"8","author":"Canny","year":"1986","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/83.862633","article-title":"Adaptive wavelet thresholding for image denoising and compression","volume":"9","author":"Chang","year":"2000","journal-title":"IEEE Trans Image Process"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","article-title":"A threshold selection method from gray-level histograms","volume":"9","author":"Otsu","year":"1979","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"ref4","first-page":"3403","article-title":"A deep learning-based approach for road surface damage detection","volume":"73","author":"Kulambayev","year":"2022","journal-title":"Comput Mat Contin"},{"key":"ref5","first-page":"2201","article-title":"Road damage detection and classification using Mask R-CNN with DenseNet backbone","volume":"65","author":"Chen","year":"2020","journal-title":"Comput Mat Contin"},{"key":"ref6","series-title":"2016 IEEE International Conference on Image Processing (ICIP)","first-page":"3708","article-title":"Road crack detection using deep convolutional neural network","author":"Zhang","year":"2016 Sep 25\u201328"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"3434","DOI":"10.1109\/TITS.2016.2552248","article-title":"Automatic road crack detection using random structured forests","volume":"17","author":"Shi","year":"2016","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"04019017","DOI":"10.1061\/(ASCE)CP.1943-5487.0000831","article-title":"Patch-based crack detection in black box images using convolutional neural networks","volume":"33","author":"Park","year":"2019","journal-title":"J Comput Civ Eng"},{"key":"ref9","unstructured":"Jocher G, Chaurasia A, Qiu J. YOLOv5 by Ultralytics; 2020 [software]. [cited 2025 Jun 4]. Available from: https:\/\/github.com\/ultralytics\/yolov5."},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2583","DOI":"10.3390\/electronics12122583","article-title":"An enhanced lightweight network for road damage detection based on deep learning","volume":"12","author":"Luo","year":"2023","journal-title":"Electronics"},{"key":"ref11","first-page":"1","article-title":"Exploring deep learning methods for computer vision applications across multiple sectors: challenges and future trends","volume":"139","author":"Ganesh","year":"2024","journal-title":"Comput Model Eng Sci"},{"key":"ref12","series-title":"2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI)","first-page":"891","article-title":"An image data augmentation algorithm based on YOLOv5s-DA for pavement distress detection","author":"Li","year":"2022 Aug 19\u201321"},{"key":"ref13","unstructured":"Li Z, Xiao X, Xie J, Fan Y, Wang W, Chen G, et al. Cycle-YOLO: a efficient and robust framework for pavement damage detection. arXiv:2405.17905. 2024."},{"key":"ref14","series-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"3456","article-title":"YOLO-Pavement: an enhanced YOLOv5-based road damage detection framework with structure-aware learning","author":"Chen","year":"2023 May 29\u2013Jun 2"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","article-title":"Squeeze-and-excitation networks","volume":"42","author":"Hu","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref16","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11531","article-title":"ECA-Net: efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020 Jun 13\u201319"},{"key":"ref17","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021 Jun 20\u201325"},{"key":"ref18","series-title":"European Conference on Computer Vision (ECCV)","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018 Sep 8\u201314"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"122804","DOI":"10.1016\/j.eswa.2023.122804","article-title":"SAM-Net: self-attention based feature matching with spatial transformers and knowledge distillation","volume":"242","author":"Kelenyi","year":"2024","journal-title":"Expert Syst Appl"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Xia Z, Pan X, Song S, Li LE, Huang G. Vision transformer with deformable attention. arXiv:2201.00520. 2022.","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref21","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, et al. YOLOv6: a single-stage object detection framework for industrial applications. arXiv:2209.02976. 2022."},{"key":"ref22","series-title":"Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023 Jun 17\u201324"},{"key":"ref23","unstructured":"Reis D, Kupec J, Hong J, Daoudi A. Real-time flying object detection with YOLOv8. arXiv:2305.09972. 2024. doi:10.48550\/arXiv.2305.09972."},{"key":"ref24","unstructured":"Fang Y, Liao B, Wang X, Fang J, Qi J, Wu R, et al. You only look at one sequence: rethinking transformer in vision through object detection. arXiv:2106.00666. 2021."},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, et al. DETRs beat YOLOs on real-time object detection. arXiv:2304.08069. 2024.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref26","series-title":"Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10440","article-title":"Lite-HRNet: a lightweight high-resolution network","author":"Yu","year":"2021 Jun 20\u201325"},{"key":"ref27","author":"Ren","journal-title":"Advances in Neural Information Processing Systems (NeurIPS);"},{"key":"ref28","series-title":"Proceedings of the European Conference on Computer Vision (ECCV). Vol. 9905.","first-page":"21","article-title":"SSD: single shot MultiBox detector","author":"Liu"},{"key":"ref29","first-page":"87","article-title":"GraphCrack: graph-based multi-modal attention network for road crack detection","volume":"160","author":"Liu","year":"2023","journal-title":"Neural Networks"},{"key":"ref30","first-page":"015401","article-title":"SODD-YOLOv8: an insulator defect detection algorithm based on feature enhancement and variable row convolution","volume":"36","author":"Wang","year":"2024","journal-title":"Meas Sci Technol"},{"key":"ref31","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. 2017."},{"key":"ref32","series-title":"Advances in Neural Information Processing Systems (NeurIPS); 2022 Nov 28; New Orleans, LA, USA","first-page":"12934","article-title":"EfficientFormer: vision transformers at MobileNet speed","author":"Li"},{"key":"ref33","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2018 Jun 18\u201323; Salt Lake City, UT, USA","first-page":"4510","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler"},{"key":"ref34","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13733","article-title":"RepVGG: making VGG-style convnets great again","author":"Ding","year":"2021 Jun 20\u201325"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/978-3-031-46311-2_5","author":"Cheng","year":"2023","journal-title":"Image and graphics"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.3390\/rs15133214","article-title":"Improving YOLOv7-tiny for infrared and visible light image object detection on drones","volume":"15","author":"Hu","year":"2023","journal-title":"Remote Sens"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"Terven","year":"2023","journal-title":"Mach Learn Knowl Extr"},{"key":"ref38","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017 Jul 21\u201326"},{"key":"ref39","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018 Jun 18\u201323"},{"key":"ref40","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020 Jun 13\u201319"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"123568","DOI":"10.1016\/j.eswa.2024.123568","article-title":"Attention-guided multi-granularity fusion model for video summarization","volume":"249","author":"Zhang","year":"2024","journal-title":"Expert Syst Appl"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1007\/s12559-023-10206-8","article-title":"Attention-guided multi-scale fusion network for similar objects semantic segmentation","volume":"16","author":"Yao","year":"2024","journal-title":"Cogn Comput"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"104807","DOI":"10.1016\/j.dsp.2024.104807","article-title":"TAG-fusion: two-stage attention guided multi-modal fusion network for semantic segmentation","volume":"156","author":"Zhang","year":"2025","journal-title":"Digit Signal Process"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"11002","DOI":"10.1109\/TII.2024.3397401","article-title":"Multiscale channel attention-driven graph dynamic fusion learning method for robust fault diagnosis","volume":"20","author":"Zhang","year":"2024","journal-title":"IEEE Trans Ind Inform"},{"key":"ref45","series-title":"Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI); 2021 Jan 7\u201315; Yokohama, Japan","first-page":"3933","article-title":"Efficient context-aware neural machine translation with layer-wise weighting and input-aware gating","author":"Xu"},{"key":"ref46","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Mexico City, Mexico","first-page":"783","article-title":"Trusting your evidence: hallucinate less with context-aware decoding","author":"Shi","year":"2024"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"104437","DOI":"10.1016\/j.bspc.2022.104437","article-title":"CANet: context aware network with dual-stream pyramid for medical image segmentation","volume":"81","author":"Xie","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1016\/j.neucom.2022.01.005","article-title":"Review the state-of-the-art technologies of semantic segmentation based on deep learning","volume":"493","author":"Mo","year":"2022","journal-title":"Neurocomputing"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.1016\/j.procs.2024.02.029","article-title":"Natural language processing approaches in industrial maintenance: a systematic literature review","volume":"232","author":"Zhong","year":"2024","journal-title":"Procedia Comput Sci"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"121168","DOI":"10.1016\/j.eswa.2023.121168","article-title":"A survey on multimodal bidirectional machine learning translation of image and natural language processing","volume":"235","author":"Nam","year":"2024","journal-title":"Expert Syst Appl"},{"key":"ref51","series-title":"Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV)","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015 Dec 7\u201313"},{"key":"ref52","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016 Jun 27\u201330"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"169113","DOI":"10.1016\/j.scitotenv.2023.169113","article-title":"Comparison between U-shaped structural deep learning models to detect landslide traces","volume":"912","author":"Dang","year":"2024","journal-title":"Sci Total Environ"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"25525","DOI":"10.1038\/s41598-024-76886-w","article-title":"WiTUnet: a U-shaped architecture integrating CNN and Transformer for improved feature alignment and local information fusion","volume":"14","author":"Wang","year":"2024","journal-title":"Sci Rep"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.3390\/s24031005","article-title":"Semantic segmentation of surface cracks in urban comprehensive pipe galleries based on global attention","volume":"24","author":"Zhou","year":"2024","journal-title":"Sensors"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"4073","DOI":"10.3390\/app14104073","article-title":"Attention-based two-branch hybrid fusion network for medical image segmentation","volume":"14","author":"Liu","year":"2024","journal-title":"Appl Sci"},{"key":"ref57","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh IH, Liao HYM. YOLOv9: learning what you want to learn using programmable gradient information. arXiv:2402.13616. 2024.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref58","doi-asserted-by":"crossref","unstructured":"Wang A, Chen H, Liu L, Chen K, Lin Z, Han J, et al. YOLOv10: real-time end-to-end object detection. arXiv:2405.14458. 2024.","DOI":"10.52202\/079017-3429"},{"key":"ref59","doi-asserted-by":"crossref","unstructured":"Xiao X, Li Z, Wang W, Xie J, Lin H, Roy SK, et al. TD-RD: a top-down benchmark with real-time framework for road damage detection. arXiv:2501.14302. 2025.","DOI":"10.1109\/ICASSP49660.2025.10888616"},{"key":"ref60","unstructured":"Yu G, Chang Q, Lv W, Xu C, Cui C, Ji W, et al. PP-PicoDet: a better real-time object detector on mobile devices. arXiv:2111.00902. 2021."}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-84-3\/TSP_CMC_66188\/TSP_CMC_66188.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T05:45:33Z","timestamp":1776923133000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v84n3\/63183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.066188","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2025-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-30","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}