Zecheng Yu

The University of Tokyo

Papers

1

Total Citations

12

H-Index

1

About

Zecheng Yu is a rising researcher in computer vision and embodied AI, with a primary focus on understanding human-object interactions from egocentric perspectives. His work centers on the concept of object affordance—the action possibilities that objects offer based on human motor capabilities and physical properties. Yu’s most cited paper, "Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos" (2023, 12 citations), introduces a novel annotation framework that captures nuanced, temporally-aware affordance labels in first-person video. This contribution addresses a critical gap in the field, enabling more accurate action anticipation and robot imitation learning by grounding AI systems in real-world human behavior. By providing fine-grained affordance data, Yu’s work directly supports downstream tasks in robotics and activity recognition, where understanding not just what an object is, but what can be done with it, is essential. His research bridges perception and action, offering a foundational resource for developing intelligent agents that can learn from and interact with their environment as humans do. As an early-career researcher, Yu’s focused contributions to affordance understanding signal a promising trajectory in the intersection of computer vision, cognitive science, and robotics.

Research Focus

Key Achievements

1
H-Index
1
Papers
12
Total Citations
12
Avg Citations/Paper
🏆 Most Cited Paper
Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos
12 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: The University of Tokyo

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago