My recent studies are focused on generative AI, world models, and multimodal large language models. My research aims to provide theory-grounded, data-driven solutions for improving the performance, safety, and accessiblity of complex engineered systems including automated driving systems, civil infrastructure systems, and human-technology systems.
I am particularly interested in research problems arising from:
Perception, planning, and control for automated driving systems
Multimodal sensor data analysis for civil infrastructure condition assessment and monitoring
Human sensing, understanding, and performance metrology for human-technology systems
Building the Data Infrastructure for Monitoring Rural Roads
USDOT through Rural Safe Efficient Advanced Transporta7on (R-SEAT) Center
06/01/2025-03/31/2027
Understanding Safety-critical Driving Scenes in Rural Roads
USDOT through Rural Safe Efficient Advanced Transporta7on (R-SEAT) Center
06/01/2025-03/31/2027
Most of my papers can be searched on Google Scholar. The following is some of my recent work.
Automated Driving Systems
Liang, K., Li, K., Biswas, D., Ding, Y., Hu, X., & Qin*, R. (2027). NACrash: A densely annotated north American crash video dataset and benchmark for multimodal large language models. To appear in Proceedings of Winter Conference on Applications of Computer Vision 2027 (WACV). Orlando, Florida, USA. January 4-8, 2027. [code]
Li, K., Liang, K., Biswas, D., Ding, Y., Hu, X., & Qin*, R. (2026). CCFM: Collision-constrained flow matching for safety-critical scenario generation. In Proceedings of the 19th European Conference on Computer Vision (ECCV), 86-103. September 8-12, 2026. Malmö, Sweden. [paper][code]
Li, K., Zhang, C., Ding, Y., Hu, X., & Qin, R. (2026). Multi-attribute scene identification for autonomous vehicles: acquiring and accumulating knowledge from diverse datasets. IEEE Transactions on Intelligent Vehicles 10 (11): 1143-1158. [paper][code].
Liang, K., Li, K., Hu, X., & Qin*, R. (2026). CrashChat: A multimodal large language model for multitask traffic crash video analysis. In Proceedings of the 28th International Conference on Pattern Recognition (ICPR). Lyon, France. August 17-22, 2026. [paper] [code]
Li, K., Yang, T., Liang, K., Hu, X., & Qin*, R. (2026). HMPDM: A diffusion model for driving video prediction with historical motion priors. In Proceedings of IEEE Intelligent Vehicle Symposium (IV) 2026. Detroit, MI, USA. June 22-25, 2026. [paper] [code]
Karim, M.M., Qin*, R., & Yin, Z. (2023). An attention-guided multistream feature fusion network for early localization of risky traffic agents in driving videos. IEEE Transactions on Intelligent Vehicles 9(1), 1792-1803. [paper] [code]
Karim, M.M., Li, Y., Qin*, R., & Yin, Z. (2022). A dynamic spatial-temporal attention network for early anticipation of traffic accidents. IEEE Transaction on Intelligent Transportation Systems 23(7): 9590-9600. [paper] [code]
Karim, M.M., Li, Y., & Qin*, R.(2022). Toward explainable artificial intelligence (XAI) for early anticipation of traffic accidents. Transportation Research Record 2626 (6): 743-755. [paper] [code]
Li, Y., Karim, M.M., Qin*, R., Sun, Z., Wang, Z., & Yin, Z. (2021). Crash report data analysis for creating scenario-wise, spatio-temporal attention guidance to support computer vision-based perception of fatal crash risks. Accident Analysis & Prevention 151, 105962. [paper]
Civil Infrastruture Systems
Zhang, C., Liu, C., Li, K., Yin, Z., & Qin*, R. (2025). Inspector gaze‐guided multitask learning for explainable structural damage assessment. Computer‐Aided Civil and Infrastructure Engineering, 40(30), 5824-5841. [paper] [code]
Zhang, C., Huang, S., & Qin*, R. (2025). When segment anything model meets inventorying of roadway Assets. International Journal of Transportation Science and Technology, 20, 1-14. [paper]
Zhang, C., Li, K., Yin, Z., & Qin*, R. (2024). Weakly‐supervised structural component segmentation via scribble annotations. Computer-Aided Civil and Infrastructure Engineering, 40(5), 561-578. [paper] [code]
Zhang, C., Yin, Z., & Qin*, R. (2024). Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for automated structural condition assessment in visual inspection. Automation in Construction 159, 105292. [paper] [code]
Zhang, C., Karim, M.M., & Qin*, R. (2023). A multitask deep learning model for parsing bridge elements and segmenting defects in bridge inspection images. Transportation Research Record, 2677(7), 693-704. [paper] [code]
Karim, M.M., Qin*, R., Yin, Z., & Chen, G. (2022). A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos. Structural Health Monitoring 21(3), 835-852. [paper] [code]
Zhao, T., Yin, Z., Qin, R., & Chen, G. (2019). Image data analytics to support engineers’ decision-making. In Proceedings of the 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure (SHMII-9), St. Louis, MO, USA. August 4-7, 2019. [manuscript]
Human-Technology Systems
Sultana, J., Qin, R., Yin, Z. (2027). EgoWaste: A hierarchical egocentric waste dataset for material recovery. To appear in Proceedings of Winter Conference on Applications of Computer Vision 2027 (WACV). Orlando, Florida, USA. January 4-8, 2027. [code]
Sultana, J., Qin, R., Yin, Z. (2026). Radgaze-LLM: Anatomical region-grounded radiology report generation via learning from expert gaze. In Proceedings of the 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI). London, United Kindom. April 08-11, 2026 [paper] [code]
Li, Y., Zhang, D., Dong, P., Yao, S., & Qin*, R. (2025). A surface electromyography-based deep learning model for guiding semi-autonomous drones in road infrastructure inspection. Computer-Aided Civil and Infrastructure Engineering. [paper] [code]
Sultana, J., Qin, R. & Yin, Z. (2024). Seeing through expert's eyes: Leveraging radiologist eye gaze and speech report with graph neural networks for chest X-ray image classification. In Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 2579-2595. [paper]
Li, Y., Parson, A., Wang, B., Dong, P., Yao, S., & Qin*, R. (2022). A multi-tasking model of speaker-keyword classification for keeping human in the loop of drone-assisted inspection. Engineering Applications of Artificial Intelligence, 117 (Part A), 105597. [paper] [code]
Li, Y., Karim, M.M., & Qin*, R. (2022). A virtual reality-based training and assessment system for inspector-drone cooperative bridge inspection. IEEE Transactions on Human Machine Systems, 52(4), 591-601. [paper] [code]
Li, Y., Wang, B., Li, W., & Qin*, R. (2022). Simulation study of passing drivers’ responses to the automated truck-mounted attenuator system in road maintenance. Transportation Research Record. [paper] [code]
Li, Y., Karim, M.M., Qin*, R. (2023). A gaze data-based comparative study to build a trustworthy human-AI collaboration in crash anticipation. ASCE 2023 International Conference on Transportation Development (ICTD). Austin, TX, USA. June 14-17, 2023. [paper] [code]
Al-Amin, M., Qin*, R., Moniruzzaman, M., Yin. Z., Tao, W., & Leu, M.C. (2023). An individualized system of skeletal data-based CNN classifiers for action recognition in manufacturing assembly. Journal of Intelligent Manufacturing 34: 633-649. [paper]
Al-Amin, M., Qin*, R., Tao, W., Doell, D., Lingard, R., Yin, Z., & Leu, M.C. (2022). Fusing and refining CNN models for assembly action recognition in smart manufacturing. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science 236(4), 2046-2059. [paper]
Al-Amin, M., Tao, W., Doell, D., Lingard, R., Yin, Z., Leu, M.C., & Qin*, R. (2019). Action recognition in manufacturing assembly using multimodal sensor fusion. Procedia Manufacturing 39, 158-167. DOI: 10.1016/j.promfg.2020.01.288. [paper]