Jing‐Tao Wu

Papers

Total Citations

H-Index

About

Jing‐Tao Wu is a researcher specializing in computer vision and intelligent transportation systems, with a particular focus on object detection in complex, crowded environments. His most notable contribution is the development of a multi-scale feature fusion framework enhanced by attention mechanisms, designed to improve the accuracy and robustness of detecting objects—such as vehicles and pedestrians—in dense, real-world road scenes. This work, published in 2024 and already garnering 13 citations, addresses a critical challenge in autonomous driving and traffic surveillance, where traditional detectors often fail due to occlusion and scale variation. Wu’s approach integrates hierarchical feature maps with learnable attention weights, enabling the model to prioritize salient regions and adapt to varying object sizes. This innovation not only advances the state of the art in crowded scene analysis but also holds practical promise for safer, more reliable perception systems. With his research bridging deep learning and applied transportation safety, Wu is establishing himself as an emerging voice in the field, and his growing citation record reflects the immediate relevance of his work to both academic and industrial communities.