{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:17:14Z","timestamp":1783210634208,"version":"3.54.6"},"reference-count":51,"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":["2023XAGG0089"],"award-info":[{"award-number":["2023XAGG0089"]}],"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":["52525204"],"award-info":[{"award-number":["52525204"]}],"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":["52232012"],"award-info":[{"award-number":["52232012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005064","name":"Hebei Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["252F0802D"],"award-info":[{"award-number":["252F0802D"]}],"id":[{"id":"10.13039\/501100005064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113952","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:48:40Z","timestamp":1778546920000},"page":"113952","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PD","title":["MASC: Joint motion-aware and VLM-semantic augmentation for contextual traffic anomaly detection"],"prefix":"10.1016","volume":"179","author":[{"given":"Hao","family":"Tong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengcheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dejie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiguang","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113952_bib0001","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.1109\/TCSVT.2023.3307655","article-title":"Vision-based traffic accident detection and anticipation: a survey","volume":"34","author":"Fang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113952_bib0002","unstructured":"W. Zhou, L. Zhao, R. Zhang, Y. Cui, H. Huang, K. Qie, C. Wang, Vision technologies with applications in traffic surveillance systems: a holistic survey, (2024). https:\/\/doi.org\/10.48550\/arXiv.2412.00348."},{"key":"10.1016\/j.patcog.2026.113952_bib0003","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1109\/TNNLS.2021.3083152","article-title":"Robust unsupervised video anomaly detection by multipath frame prediction","volume":"36","author":"Wang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0004","first-page":"17","article-title":"Cognitive traffic accident anticipation","volume":"16","author":"Li","year":"2024","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"10.1016\/j.patcog.2026.113952_bib0005","series-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"10711","article-title":"Who make drivers stop? towards driver-centric risk assessment: risk object identification via causal inference","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113952_bib0006","series-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"273","article-title":"Unsupervised traffic accident detection in first-person videos","author":"Yao","year":"2019"},{"key":"10.1016\/j.patcog.2026.113952_bib0007","doi-asserted-by":"crossref","first-page":"9601","DOI":"10.1109\/TITS.2022.3157254","article-title":"Traffic accident detection via self-supervised consistency learning in driving scenarios","volume":"23","author":"Fang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111789","article-title":"A memory-augmented multi-task collaborative framework for unsupervised traffic anomaly detection in driving videos","volume":"168","author":"Liang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113952_bib0009","first-page":"1","article-title":"PromptTAD: Object-prompt enhanced traffic anomaly detection","author":"Qiu","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.patcog.2026.113952_bib0010","unstructured":"Y. Yao, M. Xu, C. Choi, D.J. Crandall, E.M. Atkins, B. Dariush, Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems, (2019). http:\/\/arxiv.org\/abs\/1809.07408 (accessed November 2, 2024)."},{"key":"10.1016\/j.patcog.2026.113952_bib0011","doi-asserted-by":"crossref","first-page":"8684","DOI":"10.1109\/TCSVT.2024.3390173","article-title":"Text-Driven Traffic Anomaly Detection With Temporal High-Frequency Modeling in Driving Videos","volume":"34","author":"Liang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113952_bib0012","series-title":"IEEE International Automated Vehicle Validation Conference (IAVVC)","first-page":"1","article-title":"Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding","author":"Lohner","year":"2024"},{"key":"10.1016\/j.patcog.2026.113952_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110898","article-title":"Semantic-driven dual consistency learning for weakly supervised video anomaly detection","volume":"157","author":"Su","year":"2025","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.patcog.2026.113952_bib0014","unstructured":"X. Guo, R. Zhang, Y. Duan, Y. He, C. Zhang, S. Liu, L. Chen, DriveMLLM: A benchmark for spatial understanding with multimodal large language models in autonomous driving, (2024). https:\/\/doi.org\/10.48550\/arXiv.2411.13112."},{"key":"10.1016\/j.patcog.2026.113952_bib0015","doi-asserted-by":"crossref","unstructured":"K. Luo, J. Ji, T. He, R. Xu, Y. Xie, D. Anguelov, M. Tan, Enhanced motion forecasting with plug-and-play multimodal large language models, (2025). https:\/\/doi.org\/10.48550\/arXiv.2510.17274.","DOI":"10.1109\/IROS60139.2025.11246909"},{"key":"10.1016\/j.patcog.2026.113952_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112016","article-title":"A video anomaly detection framework based on semantic consistency and multi-attribute feature complementarity","volume":"170","author":"Wang","year":"2026","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.patcog.2026.113952_bib0017","first-page":"1","article-title":"Deep learning for video anomaly detection: a review","author":"Wu","year":"2026","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0018","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6536","article-title":"Future frame prediction for anomaly detection - a new baseline","author":"Liu","year":"2018"},{"key":"10.1016\/j.patcog.2026.113952_bib0019","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Nie, C. Long, Q. Zhang, G. Li, A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction, (2021). https:\/\/doi.org\/10.48550\/arXiv.2108.06852.","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"10.1016\/j.patcog.2026.113952_bib0020","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s11760-020-01740-1","article-title":"Residual spatiotemporal autoencoder for unsupervised video anomaly detection","volume":"15","author":"Deepak","year":"2021","journal-title":"SIViP"},{"key":"10.1016\/j.patcog.2026.113952_bib0021","doi-asserted-by":"crossref","unstructured":"J. Lyu, M. Zhao, J. Hu, X. Huang, S. Du, C. Shi, Z. Lv, Moba: motion memory-augmented deblurring autoencoder for video anomaly detection, (2024). https:\/\/doi.org\/10.2139\/ssrn.5078004.","DOI":"10.2139\/ssrn.5078004"},{"key":"10.1016\/j.patcog.2026.113952_bib0022","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1109\/TITS.2016.2601655","article-title":"Anomaly detection in traffic scenes via spatial-aware motion reconstruction","volume":"18","author":"Yuan","year":"2017","journal-title":"IEEE Trans. Intell. Trans. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0023","series-title":"Proceedings of the 28th ACM International Conference on Multimedia, ACM, Seattle WA USA","first-page":"2682","article-title":"Uncertainty-based traffic accident anticipation with spatio-temporal relational learning","author":"Bao","year":"2020"},{"key":"10.1016\/j.patcog.2026.113952_bib0024","first-page":"6590","article-title":"Memory-augmented online video anomaly detection","author":"Rossi","year":"2024","journal-title":"IEEE"},{"key":"10.1016\/j.patcog.2026.113952_bib0025","doi-asserted-by":"crossref","first-page":"19772","DOI":"10.1109\/TITS.2022.3147826","article-title":"Spatio-temporal feature encoding for traffic accident detection in VANET environment","volume":"23","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0026","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/TITS.2018.2819827","article-title":"Predict vehicle collision by TTC from motion using a single video camera","volume":"20","author":"Kilicarslan","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0027","series-title":"2020 IEEE 17th India Council International Conference (INDICON)","first-page":"1","article-title":"Computer vision based accident detection for autonomous vehicles","author":"Chand","year":"2020"},{"key":"10.1016\/j.patcog.2026.113952_bib0028","series-title":"2019 IEEE Intelligent Transportation Systems Conference - ITSC","first-page":"3100","article-title":"Risky action recognition in lane change video clips using deep spatiotemporal networks with segmentation mask transfer","author":"Yurtsever","year":"2019"},{"key":"10.1016\/j.patcog.2026.113952_bib0029","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TEVC.2022.3215743","article-title":"Evolutionary multiform optimization with two-stage bidirectional knowledge transfer strategy for point cloud registration","volume":"28","author":"Wu","year":"2024","journal-title":"IEEE Trans. Evol. Computat."},{"key":"10.1016\/j.patcog.2026.113952_bib0030","doi-asserted-by":"crossref","first-page":"2804","DOI":"10.1109\/TEVC.2025.3526779","article-title":"Multitask multiscale feature selection for point cloud registration","volume":"29","author":"Wu","year":"2025","journal-title":"IEEE Trans. Evol. Computat."},{"key":"10.1016\/j.patcog.2026.113952_bib0031","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/TPAMI.2022.3150763","article-title":"DoTA: unsupervised detection of traffic anomaly in driving videos","volume":"45","author":"Yao","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113952_bib0032","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-Language Models for Vision Tasks: A Survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113952_bib0033","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.1109\/TCSVT.2025.3566695","article-title":"Video understanding with large language models: a survey","volume":"36","author":"Tang","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113952_bib0034","article-title":"Video chat : chat-centric video understanding","volume":"200102","author":"Li","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.patcog.2026.113952_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2087","article-title":"LLaVA-CoT: let vision language models reason step-by-step","author":"Xu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113952_bib0036","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"14455","article-title":"SpatialVLM: endowing vision-language models with spatial reasoning capabilities","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.113952_bib0037","unstructured":"Y. Yang, K. Lee, B. Dariush, Y. Cao, S.-Y. Lo, Follow the rules: reasoning for video anomaly detection with large language models, (2024). http:\/\/arxiv.org\/abs\/2407.10299 (accessed October 29, 2024)."},{"key":"10.1016\/j.patcog.2026.113952_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103388","article-title":"A survey on multi-modal and weakly supervised approaches for robust anomaly detection in video data","volume":"126","author":"Barbosa","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113952_bib0039","unstructured":"B. Jiang, S. Chen, B. Liao, X. Zhang, W. Yin, Q. Zhang, C. Huang, W. Liu, X. Wang, Senna: bridging large vision-language models and end-to-end autonomous driving, (2024). https:\/\/doi.org\/10.48550\/arXiv.2410.22313."},{"key":"10.1016\/j.patcog.2026.113952_bib0040","series-title":"Neural Information Processing Systems (NeurIPS)","first-page":"139751","article-title":"Learning to understand open-world video anomalies","author":"Tang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113952_bib0041","series-title":"IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","first-page":"958","article-title":"A Survey on Multimodal Large Language Models for Autonomous Driving","author":"Cui","year":"2024"},{"key":"10.1016\/j.patcog.2026.113952_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.commtr.2024.100146","article-title":"Harnessing multimodal large language models for traffic knowledge graph generation and decision-making","volume":"4","author":"Kuang","year":"2024","journal-title":"Commun. Transp. Res."},{"key":"10.1016\/j.patcog.2026.113952_bib0043","series-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","article-title":"Large language models powered context-aware motion prediction in autonomous driving","author":"Zheng","year":"2024"},{"key":"10.1016\/j.patcog.2026.113952_bib0044","doi-asserted-by":"crossref","unstructured":"C.-Y. Wang, I.-H. Yeh, H.-Y.M. Liao, YOLOv9: learning what you want to learn using programmable gradient information, (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.13616.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"10.1016\/j.patcog.2026.113952_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2025.105368","article-title":"An explainable end-to-end autonomous driving framework based on large language model and vision modality fusion: design and application of DriveLLM-V","volume":"181","author":"Hou","year":"2025","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"key":"10.1016\/j.patcog.2026.113952_bib0046","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, P. Doll\u00e1r, R. Girshick, Segment Anything, (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.02643.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.patcog.2026.113952_bib0047","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0048","doi-asserted-by":"crossref","first-page":"1501","DOI":"10.1109\/TPAMI.2024.3509860","article-title":"Deep loss convexification for learning iterative models","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113952_bib0049","doi-asserted-by":"crossref","first-page":"4959","DOI":"10.1109\/TITS.2020.3044678","article-title":"DADA: driver attention prediction in driving accident scenarios","volume":"23","author":"Fang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.113952_bib0050","unstructured":"S. Bai, K. Chen, X. Liu, J. Wang, W. Ge, S. Song, K. Dang, P. Wang, S. Wang, J. Tang, H. Zhong, Y. Zhu, M. Yang, Z. Li, J. Wan, P. Wang, W. Ding, Z. Fu, Y. Xu, J. Ye, X. Zhang, T. Xie, Z. Cheng, H. Zhang, Z. Yang, H. Xu, J. Lin, Qwen2.5-VL Technical Report, (2025). https:\/\/doi.org\/10.48550\/arXiv.2502.13923."},{"key":"10.1016\/j.patcog.2026.113952_bib0051","series-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Temporal recurrent networks for online action detection","author":"Xu","year":"2019"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009179?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009179?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T23:40:17Z","timestamp":1783208417000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":51,"alternative-id":["S0031320326009179"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113952","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MASC: Joint motion-aware and VLM-semantic augmentation for contextual traffic anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113952","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":"113952"}}