{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:29:23Z","timestamp":1777876163213,"version":"3.51.4"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62502532"],"award-info":[{"award-number":["62502532"]}],"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":[[2026,7]]},"DOI":"10.1016\/j.aei.2026.104594","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T12:53:31Z","timestamp":1773233611000},"page":"104594","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Domain textual knowledge-enhanced few-shot utility tunnel video anomaly detection with multimodal large language models"],"prefix":"10.1016","volume":"73","author":[{"given":"Baijian","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7317-507X","authenticated-orcid":false,"given":"Hai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.aei.2026.104594_b1","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.tust.2018.07.024","article-title":"Urban utility tunnels as a long-term solution for the sustainable revitalization of historic centres: The case study of Pamplona-Spain","volume":"81","author":"Valdenebro","year":"2018","journal-title":"Tunn. Undergr. Space Technol."},{"key":"10.1016\/j.aei.2026.104594_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.tust.2021.104243","article-title":"Applications of utility tunnels for natural gas pipelines","volume":"122","author":"Apak","year":"2022","journal-title":"Tunn. Undergr. Space Technol."},{"key":"10.1016\/j.aei.2026.104594_b3","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.tust.2018.03.006","article-title":"Development and applications of common utility tunnels in China","volume":"76","author":"Wang","year":"2018","journal-title":"Tunn. Undergr. Space Technol."},{"issue":"11","key":"10.1016\/j.aei.2026.104594_b4","doi-asserted-by":"crossref","first-page":"4707","DOI":"10.1016\/j.eswa.2013.02.031","article-title":"Criticality and threat analysis on utility tunnels for planning security policies of utilities in urban underground space","volume":"40","author":"Canto-Perello","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.aei.2026.104594_b5","first-page":"51","article-title":"Risks and potential hazards in utility tunnels for urban areas","volume":"vol. 156","author":"Canto-Perello","year":"2003"},{"issue":"4","key":"10.1016\/j.aei.2026.104594_b6","article-title":"Damage identification of pipeline based on ultrasonic guided wave and wavelet denoising","volume":"12","author":"Xu","year":"2021","journal-title":"J. Pipeline Syst. Eng. Pr."},{"key":"10.1016\/j.aei.2026.104594_b7","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/j.ymssp.2019.04.054","article-title":"Experimental and theoretical study on a novel multi-dimensional vibration isolation and mitigation device for large-scale pipeline structure","volume":"129","author":"Xu","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"10.1016\/j.aei.2026.104594_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.engfailanal.2022.106609","article-title":"Analysis on the disaster chain evolution from gas leak to explosion in urban utility tunnels","volume":"140","author":"Xu","year":"2022","journal-title":"Eng. Fail. Anal."},{"issue":"1","key":"10.1016\/j.aei.2026.104594_b9","article-title":"Dynamic analysis and parameter optimization of pipelines with multidimensional vibration isolation and mitigation device","volume":"12","author":"Xu","year":"2021","journal-title":"J. Pipeline Syst. Eng. Pr."},{"key":"10.1016\/j.aei.2026.104594_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103309","article-title":"A novel method for leakage monitoring in network-level urban medium-and low-pressure natural gas pipelines combining information theory and light gradient boosting","volume":"65","author":"Huang","year":"2025","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103471","article-title":"Physics-informed CGAN and multi-scale attention CNN for pipeline leakage diagnosis under imbalanced data","volume":"66","author":"Zhu","year":"2025","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102492","article-title":"A classification and quantitative assessment method for internal and external surface defects in pipelines based on ASTC-net","volume":"61","author":"Yuan","year":"2024","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.104022","article-title":"Multimodal feature fusion deep learning for spatiotemporal prediction of deformation and environmental impacts in pipe-roof tunnel construction","volume":"69","author":"Zhang","year":"2026","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.104201","article-title":"Automatic multi-anomaly detection of pipelines with ensemble deep learning-based computer vision","volume":"70","author":"Moghaddas","year":"2026","journal-title":"Adv. Eng. Informatics"},{"issue":"1","key":"10.1016\/j.aei.2026.104594_b15","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1109\/TITS.2021.3122906","article-title":"ADS-lead: Lifelong anomaly detection in autonomous driving systems","volume":"24","author":"Han","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aei.2026.104594_b16","series-title":"Hybrid video anomaly detection for anomalous scenarios in autonomous driving","author":"Bogdoll","year":"2024"},{"issue":"3","key":"10.1016\/j.aei.2026.104594_b17","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.1109\/TITS.2020.2975043","article-title":"End-to-end autonomous driving risk analysis: A behavioural anomaly detection approach","volume":"22","author":"Ryan","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.aei.2026.104594_b18","series-title":"European Conference on Computer Vision","first-page":"206","article-title":"Anovox: A benchmark for multimodal anomaly detection in autonomous driving","author":"Bogdoll","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b19","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"341","article-title":"A revisit of sparse coding based anomaly detection in stacked rnn framework","author":"Luo","year":"2017"},{"key":"10.1016\/j.aei.2026.104594_b20","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20392","article-title":"A new comprehensive benchmark for semi-supervised video anomaly detection and anticipation","author":"Cao","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b21","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12742","article-title":"Anomaly detection in video via self-supervised and multi-task learning","author":"Georgescu","year":"2021"},{"key":"10.1016\/j.aei.2026.104594_b22","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"934","article-title":"Any-shot sequential anomaly detection in surveillance videos","author":"Doshi","year":"2020"},{"key":"10.1016\/j.aei.2026.104594_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103240","article-title":"CPIR: Multimodal industrial anomaly detection via latent bridged cross-modal prediction and intra-modal reconstruction","volume":"65","author":"Shangguan","year":"2025","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103792","article-title":"Multimodal feature cooperative refinement for few-shot anomaly detection","volume":"68","author":"Xu","year":"2025","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103953","article-title":"Enhancing aero-engine blade few-shot anomaly detection with visual-language multi-modal models under domain shift conditions","volume":"69","author":"Tang","year":"2026","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103886","article-title":"Deviation capture networks for anomaly detection","volume":"69","author":"Yan","year":"2026","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.103064","article-title":"Simple and effective frequency-aware image restoration for industrial visual anomaly detection","volume":"64","author":"Liu","year":"2025","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.104070","article-title":"From generation to classification: A PGDM\u2013SACM framework for anomaly detection in the finishing mill process under data scarcity","volume":"69","author":"Lee","year":"2026","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104594_b29","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13588","article-title":"A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction","author":"Liu","year":"2021"},{"key":"10.1016\/j.aei.2026.104594_b30","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15425","article-title":"Learning normal dynamics in videos with meta prototype network","author":"Lv","year":"2021"},{"key":"10.1016\/j.aei.2026.104594_b31","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"733","article-title":"Learning temporal regularity in video sequences","author":"Hasan","year":"2016"},{"key":"10.1016\/j.aei.2026.104594_b32","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18527","article-title":"Harnessing large language models for training-free video anomaly detection","author":"Zanella","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b33","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.aei.2026.104594_b34","series-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"10.1016\/j.aei.2026.104594_b35","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104594_b36","series-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding","author":"Zhang","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b37","series-title":"Holmes-vad: Towards unbiased and explainable video anomaly detection via multi-modal llm","author":"Zhang","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b38","series-title":"Video anomaly detection and explanation via large language models","author":"Lv","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b39","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15180","article-title":"Imagebind: One embedding space to bind them all","author":"Girdhar","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b40","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"11975","article-title":"Sigmoid loss for language image pre-training","author":"Zhai","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b41","series-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","first-page":"1","author":"Yang","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b42","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104594_b43","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104594_b44","series-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b45","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"13843","article-title":"Holmes-vau: Towards long-term video anomaly understanding at any granularity","author":"Zhang","year":"2025"},{"key":"10.1016\/j.aei.2026.104594_b46","first-page":"6074","article-title":"Vadclip: Adapting vision-language models for weakly supervised video anomaly detection","volume":"vol. 38","author":"Wu","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b47","series-title":"European Conference on Computer Vision","first-page":"304","article-title":"Follow the rules: Reasoning for video anomaly detection with large language models","author":"Yang","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b48","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"SUVAD: Semantic understanding based video anomaly detection using MLLM","author":"Gao","year":"2025"},{"key":"10.1016\/j.aei.2026.104594_b49","series-title":"Anyanomaly: Zero-shot customizable video anomaly detection with lvlm","author":"Ahn","year":"2025"},{"key":"10.1016\/j.aei.2026.104594_b50","series-title":"Verbalized machine learning: Revisiting machine learning with language models","author":"Xiao","year":"2024"},{"issue":"8055","key":"10.1016\/j.aei.2026.104594_b51","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1038\/s41586-025-08661-4","article-title":"Optimizing generative AI by backpropagating language model feedback","volume":"639","author":"Yuksekgonul","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.aei.2026.104594_b52","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"8679","article-title":"Vera: Explainable video anomaly detection via verbalized learning of vision-language models","author":"Ye","year":"2025"},{"key":"10.1016\/j.aei.2026.104594_b53","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.aei.2026.104594_b54","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4975","article-title":"Weakly-supervised video anomaly detection with robust temporal feature magnitude learning","author":"Tian","year":"2021"},{"key":"10.1016\/j.aei.2026.104594_b55","doi-asserted-by":"crossref","first-page":"4505","DOI":"10.1109\/TIP.2021.3072863","article-title":"Localizing anomalies from weakly-labeled videos","volume":"30","author":"Lv","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.aei.2026.104594_b56","series-title":"European Conference on Computer Vision","first-page":"322","article-title":"Not only look, but also listen: Learning multimodal violence detection under weak supervision","author":"Wu","year":"2020"},{"key":"10.1016\/j.aei.2026.104594_b57","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8022","article-title":"Unbiased multiple instance learning for weakly supervised video anomaly detection","author":"Lv","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b58","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6536","article-title":"Future frame prediction for anomaly detection\u2013a new baseline","author":"Liu","year":"2018"},{"key":"10.1016\/j.aei.2026.104594_b59","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6479","article-title":"Real-world anomaly detection in surveillance videos","author":"Sultani","year":"2018"},{"key":"10.1016\/j.aei.2026.104594_b60","series-title":"Motion-aware feature for improved video anomaly detection","author":"Zhu","year":"2019"},{"key":"10.1016\/j.aei.2026.104594_b61","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"4679","article-title":"Global information guided video anomaly detection","author":"Lv","year":"2020"},{"key":"10.1016\/j.aei.2026.104594_b62","series-title":"2023 IEEE International Conference on Image Processing","first-page":"3230","article-title":"Clip-tsa: Clip-assisted temporal self-attention for weakly-supervised video anomaly detection","author":"Joo","year":"2023"},{"key":"10.1016\/j.aei.2026.104594_b63","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26296","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.aei.2026.104594_b64","series-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626002867?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626002867?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T22:16:11Z","timestamp":1777587371000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1474034626002867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":64,"alternative-id":["S1474034626002867"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104594","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Domain textual knowledge-enhanced few-shot utility tunnel video anomaly detection with multimodal large language models","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104594","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":"104594"}}