Weixian Lei
Papers
1
Total Citations
6
H-Index
1
About
Weixian Lei is a researcher at the forefront of human-robot interaction and multimodal video understanding, with a focus on leveraging eye-gaze information to decode human intention. Their key research areas include egocentric vision, video question answering (VQA), and task-oriented collaboration. Lei’s major contribution is the introduction of **GazeVQA**, a pioneering dataset that integrates multiview (exocentric and egocentric) videos with eye-gaze cues for collaborative tasks—a novel endeavor in the field. This work bridges the gap between visual perception and cognitive intent, enabling robots to better interpret human actions in shared environments. With 6 citations since its 2023 publication, GazeVQA has quickly become a foundational resource for advancing human-robot collaboration. Lei’s research is notable for its practical impact on assistive robotics and interactive AI, offering a scalable framework for future studies in intention-aware systems. Their work stands out for its innovative fusion of gaze tracking with VQA, setting a new benchmark for understanding complex, real-world interactions.
Research Focus
Key Achievements
Top Papers
- 1