Hongjie Ma
Papers
3
Total Citations
177
H-Index
3
About
Hongjie Ma is a researcher whose work lies at the intersection of computer vision, robotics, and autonomous systems, with a particular focus on enabling machines to perceive and navigate complex, dynamic environments. His key research areas include object detection, pedestrian trajectory prediction, and 3D pose estimation. Ma’s most impactful contribution is the development of a Multi-Scale Feature Fusion Convolutional Neural Network for indoor small target detection (128 citations), which directly addresses the persistent challenge of accurately identifying small objects in cluttered, real-world settings—a critical capability for human-robot interaction. He further advanced the field of autonomous navigation with the STI-GAN model (41 citations), which uses spatiotemporal interactions and a generative adversarial network to predict multimodal pedestrian trajectories, helping autonomous vehicles and social robots anticipate and avoid collisions. More recently, Ma has tackled the problem of robotic grasping with an improved K-D tree ICP algorithm for object pose estimation from stereo vision (8 citations). Through these contributions, Hongjie Ma is helping to build the perceptual foundation for safer, more capable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3