Benita Wong
Papers
1
Total Citations
15
H-Index
1
About
Benita Wong is a rising researcher in computer vision and human-AI interaction, with a focus on egocentric perception and assistive intelligence. Her work centers on developing AI systems that understand and anticipate human needs from a first-person perspective, particularly through the lens of affordance reasoning—the study of action possibilities in an environment. In her highly cited paper "AssistQ: Affordance-Centric Question-Driven Task Completion for Egocentric Assistant" (2022, 15 citations), Wong introduced a novel framework that enables AI assistants to interpret natural language questions and complete tasks by reasoning about object affordances in egocentric video. This contribution bridges the gap between language understanding and visual grounding, allowing systems to not only recognize objects but also infer how they can be used to fulfill user goals. Wong's work has immediate implications for augmented reality, robotics, and assistive technologies for the visually impaired. Her research, though early in her career, has already garnered attention for its practical approach to making AI more context-aware and responsive to human intent in real-world scenarios.
Research Focus
Key Achievements
Top Papers
- 1