{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:23:25Z","timestamp":1783635805717,"version":"3.55.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U24B2064"],"award-info":[{"award-number":["U24B2064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.knosys.2026.116381","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:32:41Z","timestamp":1780759961000},"page":"116381","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FSTL-Net: A few-shot welding defect detection method based on temporal modeling and metric learning"],"prefix":"10.1016","volume":"348","author":[{"given":"Keqiang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9052-7911","authenticated-orcid":false,"given":"Shuai","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisheng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengrui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tieshuang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116381_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jmsy.2023.02.016","article-title":"Online visual monitoring method for liquid rocket engine nozzle welding based on a multi-task deep learning model","volume":"68","author":"Zhou","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.optlaseng.2023.107890","article-title":"Experimental analysis of overlap fiber laser welding for aluminum alloys: Porosity recognition and quality inspection","volume":"173","author":"Aminzadeh","year":"2024","journal-title":"Opt. Lasers Eng."},{"key":"10.1016\/j.knosys.2026.116381_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmatprotec.2022.117514","article-title":"Study on arc characteristics of different defects in pulsed micro-plasma arc welding","volume":"302","author":"Lv","year":"2022","journal-title":"J. Mater. Process. Technol."},{"key":"10.1016\/j.knosys.2026.116381_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2023.110484","article-title":"Defect detection method for high-resolution weld based on wandering Gaussian and multi-feature enhancement fusion","volume":"199","author":"Li","year":"2023","journal-title":"Mech. Syst. Signal Process."},{"key":"10.1016\/j.knosys.2026.116381_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130188","article-title":"A review of algorithms for surface defect detection in welds based on machine learning","volume":"299","author":"Zhang","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116381_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109059","article-title":"Machine learning-based in-process monitoring for laser deep penetration welding: A survey","volume":"137","author":"Lu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116381_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114174","article-title":"Multiscale welding defect detection method based on image adaptive enhancement","volume":"327","author":"Cheng","year":"2025","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112116","article-title":"Interpretable multi-task neural network modeling and particle swarm optimization of process parameters in laser welding","volume":"300","author":"Ma","year":"2024","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b9","article-title":"EfficientNet-ECA: A lightweight network based on efficient channel attention for class-imbalanced welding defects classification","volume":"62","author":"Zhang","year":"2024","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.knosys.2026.116381_b10","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.jmapro.2020.01.044","article-title":"End-to-end prediction of weld penetration: A deep learning and transfer learning based method","volume":"63","author":"Jiao","year":"2021","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.optlastec.2023.110538","article-title":"Monitoring weld penetration of laser-arc hybrid welding joints without full-penetration requirement based on deep learning","volume":"172","author":"Li","year":"2024","journal-title":"Opt. Laser Technol."},{"issue":"2","key":"10.1016\/j.knosys.2026.116381_b12","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1109\/TMI.2024.3459943","article-title":"Prototype-guided graph reasoning network for few-shot medical image segmentation","volume":"44","author":"Huang","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.knosys.2026.116381_b13","doi-asserted-by":"crossref","first-page":"4397","DOI":"10.1109\/TIP.2026.3684405","article-title":"Mask-guided proxy mining network for few-shot medical image segmentation","volume":"35","author":"Huang","year":"2026","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.116381_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115769","article-title":"SFFINet: A spatial frequency feature interaction method for few-shot chip surface defect segmentation","volume":"340","author":"Xiang","year":"2026","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110634","article-title":"Few-shot fault diagnosis of turnout switch machine based on semi-supervised weighted prototypical network","volume":"274","author":"Lao","year":"2023","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b16","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1016\/j.jmapro.2024.09.084","article-title":"A defect classification algorithm for gas tungsten arc welding process based on unsupervised learning and few-shot learning strategy","volume":"131","author":"Liu","year":"2024","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b17","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1016\/j.jmapro.2026.01.035","article-title":"A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks","volume":"160","author":"Li","year":"2026","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b18","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.jmapro.2025.02.018","article-title":"A novel few-shot learning based feature relation model for robotic welding states monitoring","volume":"138","author":"Xu","year":"2025","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110212","article-title":"Cross-attention-based multi-sensing signals fusion for penetration state monitoring during laser welding of aluminum alloy","volume":"261","author":"Cao","year":"2023","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b20","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1016\/j.jmapro.2022.11.021","article-title":"Prediction of weld back width based on top vision sensing during laser-MIG hybrid welding","volume":"84","author":"Ye","year":"2022","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121425","article-title":"Unified CNN-LSTM for keyhole status prediction in PAW based on spatial-temporal features","volume":"237","author":"Zhou","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116381_b22","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.jmapro.2020.08.028","article-title":"Prediction of welding quality characteristics during pulsed GTAW process of aluminum alloy by multisensory fusion and hybrid network model","volume":"68","author":"Chen","year":"2021","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b23","first-page":"5998","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"issue":"34","key":"10.1016\/j.knosys.2026.116381_b24","doi-asserted-by":"crossref","first-page":"24315","DOI":"10.1007\/s00521-023-09004-y","article-title":"Detection of solidification crack formation in laser beam welding videos of sheet metal using neural networks","volume":"35","author":"Huo","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.knosys.2026.116381_b25","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1016\/j.jmsy.2021.01.017","article-title":"3DSMDA-Net: An improved 3DCNN with separable structure and multi-dimensional attention for welding status recognition","volume":"62","author":"Liu","year":"2022","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.knosys.2026.116381_b26","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.jmapro.2024.01.055","article-title":"Online monitoring system for welding states of bottom-locking joints in high-speed trains via multi-information fusion and 3DCNN","volume":"113","author":"Yang","year":"2024","journal-title":"J. Manuf. Process."},{"key":"10.1016\/j.knosys.2026.116381_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.ndteint.2019.102139","article-title":"Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning","volume":"107","author":"Bacioiu","year":"2019","journal-title":"NDT E Int."},{"key":"10.1016\/j.knosys.2026.116381_b28","series-title":"Advances in Neural Information Processing Systems 30","first-page":"4077","article-title":"Prototypical networks for Few-shot learning","author":"Snell","year":"2017"},{"key":"10.1016\/j.knosys.2026.116381_b29","series-title":"Advances in Neural Information Processing Systems 29","first-page":"3630","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016"},{"key":"10.1016\/j.knosys.2026.116381_b30","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6551","article-title":"Few-shot learning with localization in realistic settings","author":"Wertheimer","year":"2019"},{"key":"10.1016\/j.knosys.2026.116381_b31","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7972","article-title":"Joint distribution matters: Deep Brownian distance covariance for Few-Shot classification","author":"Xie","year":"2022"},{"issue":"4","key":"10.1016\/j.knosys.2026.116381_b32","first-page":"1236","article-title":"Brownian distance covariance","volume":"3","author":"Sz\u00e9kely","year":"2009","journal-title":"Ann. Appl. Stat."},{"issue":"16","key":"10.1016\/j.knosys.2026.116381_b33","doi-asserted-by":"crossref","first-page":"5479","DOI":"10.3390\/ma15165479","article-title":"Development of a laser scanning machining system supporting on-the-fly machining and laser power follow-up adjustment","volume":"15","author":"Yin","year":"2022","journal-title":"Materials"},{"key":"10.1016\/j.knosys.2026.116381_b34","series-title":"2015 IEEE International Conference on Computer Vision","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"10.1016\/j.knosys.2026.116381_b35","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2625","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"Donahue","year":"2015"},{"key":"10.1016\/j.knosys.2026.116381_b36","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"Tran","year":"2018"},{"key":"10.1016\/j.knosys.2026.116381_b37","series-title":"2019 IEEE\/CVF International Conference on Computer Vision","first-page":"7083","article-title":"TSM: Temporal shift module for efficient video understanding","author":"Lin","year":"2019"},{"key":"10.1016\/j.knosys.2026.116381_b38","series-title":"2019 IEEE\/CVF International Conference on Computer Vision","first-page":"6202","article-title":"SlowFast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"10.1016\/j.knosys.2026.116381_b39","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"203","article-title":"X3D: Expanding architectures for efficient video recognition","author":"Feichtenhofer","year":"2020"},{"key":"10.1016\/j.knosys.2026.116381_b40","series-title":"An efficient 3D convolutional neural network with channel-wise, spatial-grouped, and temporal convolutions","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116381_b41","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18011","article-title":"MoLo: Motion-augmented long-short contrastive learning for few-shot action recognition","author":"Wang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116381_b42","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"38","article-title":"Efficient few-shot action recognition via multi-level post-reasoning","author":"Wu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116381_b43","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"237","article-title":"VideoMamba: State space model for efficient video understanding","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116381_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126255","article-title":"STAN: Spatio-temporal analysis network for efficient video action recognition","volume":"268","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512601107X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512601107X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:11:46Z","timestamp":1783635106000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512601107X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"alternative-id":["S095070512601107X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116381","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FSTL-Net: A few-shot welding defect detection method based on temporal modeling and metric learning","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116381","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116381"}}