Mr. Jun Tang is a researcher specializing in intelligent transportation and autonomous driving, with a strong focus on the integration of computer vision and artificial intelligence to enhance vehicular perception and decision making systems. His research primarily explores large vision foundation models and their applications in object detection, scene understanding, and adaptive driving environments. He has contributed to developing advanced detection frameworks that leverage reinforcement learning to improve recognition accuracy, robustness, and real time responsiveness in dynamic traffic conditions. Mr. Tang’s recent interests include prompt-guided object detection methods that utilize natural language and contextual cues to refine visual understanding within autonomous systems. Through his work at Chengdu Zhihui Heneng City Technology, he plays a key role in bridging the gap between theoretical AI models and practical intelligent mobility applications, fostering innovations that advance the safety, efficiency, and scalability of next generation transportation systems. His interdisciplinary approach combines deep learning, machine perception, and cognitive automation, contributing to the development of more adaptive and human like decision making in autonomous vehicles.

Profile: Orcid

Featured Publications

Tang, J., Li, D., Yang, J., Chen, J., & Yuan, R. (2025). Leveraging large visual models for enhanced object detection: An improved SAM-YOLOv5 model. Knowledge-Based Systems, 114757.

Tang, J. (2025, August 29). RT-DETR-based intelligent transportation object detection optimization method and system with prompt mechanism fusion.

Tang, J. (2025, May 27). Object detection method and system based on prompt engineering and regional text description.

Tang, J. (2025, April 11). Quantitative evaluation method and system for multimodal large models.

Tang, J. (2025, January 17). Evaluation method and system for urban governance multimodal large models based on text labeling.