{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T20:14:42Z","timestamp":1784232882952,"version":"3.55.0"},"reference-count":44,"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","award":["62501234"],"award-info":[{"award-number":["62501234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203464"],"award-info":[{"award-number":["62203464"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403078"],"award-info":[{"award-number":["62403078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.aei.2026.104875","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:52:06Z","timestamp":1780779126000},"page":"104875","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Mask decoupling framework for rail surface defect pixel-level detection"],"prefix":"10.1016","volume":"76","author":[{"given":"Jianwei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3257-6093","authenticated-orcid":false,"given":"Yuan","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefeng","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1908-6644","authenticated-orcid":false,"given":"Hongli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.aei.2026.104875_b0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102717","article-title":"Defect detection on multi-type rail surfaces via IoU decoupling and multi-information alignment","volume":"62","author":"Ni","year":"2024","journal-title":"Adv. Eng. Informat."},{"key":"10.1016\/j.aei.2026.104875_b0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2021.103596","article-title":"Real-time railroad track components inspection based on the improved YOLOv4 framework","volume":"125","author":"Guo","year":"2021","journal-title":"Autom. Construct."},{"key":"10.1016\/j.aei.2026.104875_b0015","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6501\/ac31ca","article-title":"Rail surface defect inspection via s self-reference template and similarity evaluation","volume":"33","author":"Lang","year":"2022","journal-title":"Meas. Sci. Technol."},{"issue":"3","key":"10.1016\/j.aei.2026.104875_b0020","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1109\/TIM.2018.2853958","article-title":"A Coarse-to-Fine Model for Rail Surface defect Detection","volume":"68","author":"Yu","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"10.1016\/j.aei.2026.104875_b0025","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/TII.2019.2917522","article-title":"Surface defect detection via entity sparsity pursuit with intrinsic priors","volume":"16","author":"Wang","year":"2019","journal-title":"IEEE Trans. Ind. Informat."},{"issue":"3","key":"10.1016\/j.aei.2026.104875_b0030","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1109\/TCSVT.2022.3212088","article-title":"RFS-Net: Railway track fastener segmentation network with shape guidance","volume":"33","author":"Su","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.aei.2026.104875_b0035","first-page":"13025","article-title":"Label decoupling framework for salient object detection","author":"Wei","year":"2020","journal-title":"Proc. IEEE Int. Conf. Comput. vis. Pattern Recognit."},{"issue":"12","key":"10.1016\/j.aei.2026.104875_b0040","doi-asserted-by":"crossref","first-page":"8988","DOI":"10.1109\/TII.2022.3168432","article-title":"A new cycle-consistent adversarial networks with attention mechanism for surface defect classification with small samples","volume":"18","author":"Wen","year":"2022","journal-title":"IEEE Trans. Ind. Informat."},{"issue":"12","key":"10.1016\/j.aei.2026.104875_b0045","first-page":"4763","article-title":"Railroad surface defect segmentation using a modified fully convolutional network","volume":"14","author":"Kim","year":"2020","journal-title":"KSII Trans. Internet Inf. Syst."},{"issue":"2","key":"10.1016\/j.aei.2026.104875_b0050","doi-asserted-by":"crossref","first-page":"1571","DOI":"10.1109\/JSEN.2021.3133280","article-title":"Segmentation of track surface defects based on machine vision and neural networks","volume":"22","author":"Yang","year":"2022","journal-title":"IEEE Sensors J."},{"issue":"2512808","key":"10.1016\/j.aei.2026.104875_b0055","first-page":"1","article-title":"RBNet: An ultrafast rendering-based architecture for railway defect segmentation","volume":"72","author":"Li","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"3522213","key":"10.1016\/j.aei.2026.104875_b0060","first-page":"1","article-title":"Region and edge-aware network for rail surface defect segmentation","volume":"73","author":"Qiu","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"9","key":"10.1016\/j.aei.2026.104875_b0065","doi-asserted-by":"crossref","first-page":"9667","DOI":"10.1109\/TII.2022.3233654","article-title":"Shape-consist ent one-shot unsupervised domain adaptation for rail surface defect segmentation","volume":"19","author":"Ma","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"9","key":"10.1016\/j.aei.2026.104875_b0070","doi-asserted-by":"crossref","first-page":"6870","DOI":"10.1109\/TIM.2020.2975454","article-title":"Morphological detection and extraction of rail surface defects","volume":"69","author":"Nieniewski","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"7","key":"10.1016\/j.aei.2026.104875_b0075","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1109\/TIM.2018.2803830","article-title":"Automatic visual detection system of railway surface defects with curvature filter and improved Gaussian mixture model","volume":"67","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"23","key":"10.1016\/j.aei.2026.104875_b0080","doi-asserted-by":"crossref","first-page":"7935","DOI":"10.1109\/JSEN.2017.2761858","article-title":"A hierarchical extractor-based visual rail surface inspection system","volume":"17","author":"Gan","year":"2017","journal-title":"IEEE Sensors J."},{"issue":"6","key":"10.1016\/j.aei.2026.104875_b0085","doi-asserted-by":"crossref","first-page":"5806","DOI":"10.1109\/TITS.2021.3058635","article-title":"Detection for rail surface defects via partitioned edge feature","volume":"23","author":"Ni","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.aei.2026.104875_b0090","doi-asserted-by":"crossref","first-page":"2741","DOI":"10.1109\/TSMC.2018.2827937","article-title":"Online rail surface inspection utilizing spatial consistency and continuity","volume":"50","author":"Gan","year":"2020","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"12","key":"10.1016\/j.aei.2026.104875_b0095","doi-asserted-by":"crossref","first-page":"9709","DOI":"10.1109\/TIM.2020.3002277","article-title":"EDRNet: Encoder-decoder residual network for salient object detection of strip steel surface defects","volume":"69","author":"Song","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"13","key":"10.1016\/j.aei.2026.104875_b0100","doi-asserted-by":"crossref","first-page":"15010","DOI":"10.1109\/JSEN.2023.3280117","article-title":"Automatic rail surface defect inspection using the pixelwise semantic segmentation model","volume":"23","author":"Guo","year":"2023","journal-title":"IEEE Sensors J."},{"issue":"9","key":"10.1016\/j.aei.2026.104875_b0105","doi-asserted-by":"crossref","first-page":"3629","DOI":"10.3390\/app14093629","article-title":"Rail-STrans: A rail surface defect segmentation method based on improved swin transformer","volume":"14","author":"Si","year":"2024","journal-title":"Appl. Sci."},{"issue":"5005714","key":"10.1016\/j.aei.2026.104875_b0110","first-page":"1","article-title":"Deep learning and machine vision-based inspection of rail surface defects","volume":"71","author":"Yang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"11","key":"10.1016\/j.aei.2026.104875_b0115","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1177\/03611981211019034","article-title":"Automatic rail surface defects inspection based on mask R-CNN","volume":"2675","author":"Guo","year":"2021","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"issue":"105822","key":"10.1016\/j.aei.2026.104875_b0120","article-title":"RTLSeg: A novel multi-component inspection network for railway track line based on instance segmentation","volume":"119","author":"Wei","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"8","key":"10.1016\/j.aei.2026.104875_b0125","doi-asserted-by":"crossref","first-page":"11162","DOI":"10.1109\/TITS.2021.3101053","article-title":"MRSDI-CNN: Multi-modal rail surface defect inspection system based on convolutional neural networks","volume":"23","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"108860","key":"10.1016\/j.aei.2026.104875_b0130","article-title":"Uncertainty inspired domain adaptation network for rail surface defect segmentation","volume":"135","author":"Yan","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.aei.2026.104875_b0135","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1109\/LSP.2023.3299218","article-title":"CSANet: Contour and semantic feature alignment fusion network for rail surface defect detection","volume":"30","author":"Yang","year":"2023","journal-title":"IEEE Signal Process Lett."},{"key":"10.1016\/j.aei.2026.104875_b0140","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d in Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit. (2016) 770-778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.aei.2026.104875_b0145","doi-asserted-by":"crossref","unstructured":"Z. Wu, L. Su, and Q. Huang, \u201cCascaded partial decoder for fast and accurate salient object detection,\u201d in Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit. (2019) 3907-3916.","DOI":"10.1109\/CVPR.2019.00403"},{"key":"10.1016\/j.aei.2026.104875_b0150","doi-asserted-by":"crossref","unstructured":"Z. Zhang, X. Zhang, and C. Peng et al. \u201cExfuse: Enhancing feature fusion for semantic segmentation,\u201d in Proc. Eur. Conf. Comput. Vis. (2018) 269-284.","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"10.1016\/j.aei.2026.104875_b0155","unstructured":"D. P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d in Proc. Int. Conf. Learn. Representations, (2015) 1-15."},{"key":"10.1016\/j.aei.2026.104875_b0160","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, \u201cU-Net: Convolutional networks for biomedical image segmentation,\u201d in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervention, (2015) 234-241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10.1016\/j.aei.2026.104875_b0165","doi-asserted-by":"crossref","unstructured":"H. Zhao, J. Shi, and X. Qi et al., \u201cPyramid scene parsing network,\u201d in Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit. (2017) 6230-6239.","DOI":"10.1109\/CVPR.2017.660"},{"key":"10.1016\/j.aei.2026.104875_b0170","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","article-title":"MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"Ibtehaz","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.aei.2026.104875_b0175","unstructured":"J. Fu, J. Liu, and H. Tian, et al., \u201cDual Attention Network for Scene Segmentation,\u201d in Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit. (2019) 3146-3154."},{"key":"10.1016\/j.aei.2026.104875_b0180","doi-asserted-by":"crossref","unstructured":"L. C. Chen, Y. Zhu, and G. Papandreou et al., \u201cEncoder-decoder with atrous separable convolution for semantic image segmentation,\u201d in Proc. Eur. Conf. Comput. Vis. (2018) 801-818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.aei.2026.104875_b0185","doi-asserted-by":"crossref","unstructured":"T. Xiao, Y. Liu, and B. Zhou, et al., \u201cUnified Perceptual Parsing for Scene Understanding,\u201d in Proc. Eur. Conf. Comput. Vis. (2018) 418-434.","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"10.1016\/j.aei.2026.104875_b0190","unstructured":"L. Huang, Y. Yuan, and J. Guo, et al., \u201cInterlaced Sparse Self-Attention for Semantic Segmentation,\u201d 2019, arXiv:1907.12273."},{"key":"10.1016\/j.aei.2026.104875_b0195","doi-asserted-by":"crossref","unstructured":"H. Cao, Y. Wang, and J. Chen et al., \u201cSwin-unet: Unet-like pure transformer for medical image segmentation,\u201d in Proc. Eur. Conf. Comput. Vis. (2022) 205-218.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"10.1016\/j.aei.2026.104875_b0200","unstructured":"J. Chen, Y. Lu, and Q. Yu et al., \u201cTransunet: Transformers make strong encoders for medical image segmentation,\u201d 2021, arXiv:2102.04306."},{"key":"10.1016\/j.aei.2026.104875_b0205","doi-asserted-by":"crossref","unstructured":"J. Xu, Z. Xiong, and S. P. Bhattacharyya, \u201cPIDNet: A real-time semantic segmentation network inspired by PID controllers,\u201d in Proc. IEEE Int. Conf. Comput. Vis. Pattern Recognit. (2023) 19529-19539.","DOI":"10.1109\/CVPR52729.2023.01871"},{"issue":"1","key":"10.1016\/j.aei.2026.104875_b0210","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1109\/TITS.2023.3307286","article-title":"Rethinking lightweight convolutional neural networks for efficient and high-quality pavement crack detection","volume":"25","author":"Li","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aei.2026.104875_b0215","doi-asserted-by":"crossref","unstructured":"T. Zhou, Y. Zhou, and K. He, et al., \u201cCross-level feature aggregation network for polyp segmentation,\u201d Pattern Recognit. 140 (109555) 2023.","DOI":"10.1016\/j.patcog.2023.109555"},{"issue":"107202","key":"10.1016\/j.aei.2026.104875_b0220","article-title":"Edge-guided and hierarchical aggregation network for robust medical image segmentation","volume":"101","author":"Tang","year":"2025","journal-title":"Biomed. Signal Process. Control"}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626005677?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626005677?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:55:54Z","timestamp":1784231754000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1474034626005677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":44,"alternative-id":["S1474034626005677"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104875","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mask decoupling framework for rail surface defect pixel-level detection","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104875","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":"104875"}}