Papers
1
Total Citations
3
H-Index
1
About
Yingke Xu is a leading researcher in computer vision and video understanding, with a focus on bridging the gap between controlled and real-world visual recognition. Their most notable contribution is the development of view-to-scene joint learning frameworks that enable robust activity recognition in unconstrained, "in-the-wild" videos—a critical challenge for autonomous systems and visual control. By addressing the variability in camera angles, scene contexts, and unseen action classes, Xu’s work has advanced the practical deployment of video analysis technologies. Their 2024 paper, "Recognizing Video Activities in the Wild via View-to-Scene Joint Learning," has already garnered 3 citations, signaling growing impact in the field. Xu’s research is particularly valuable for applications in surveillance, human-robot interaction, and autonomous driving, where systems must interpret actions from diverse perspectives. Through innovative approaches that simplify complex spatiotemporal modeling, Xu continues to push the boundaries of how machines understand dynamic visual environments, making their work essential reading for students and researchers tackling real-world video recognition challenges.
Research Focus
Key Achievements
Top Papers
- 1