Joya Chen

Papers

Total Citations

H-Index

About

Joya Chen is a rising researcher in embodied AI and human-robot interaction, focusing on how intelligent systems can learn from human demonstrations to assist in real-world tasks. Her work centers on affordance grounding—the ability to understand how objects can be used based on observed human interactions—and its application to egocentric vision and task completion. Chen’s most cited paper, “Affordance Grounding from Demonstration Video to Target Image” (2023, 22 citations), introduces a method for transferring hand-interaction knowledge from video demonstrations to static images, a critical step for enabling AR assistants and robots to infer object use in novel contexts. She also developed AssistQ (2022, 15 citations), an affordance-centric dataset for question-driven task completion in egocentric settings, and GazeVQA (2023, 6 citations), a video question answering dataset that integrates eye-gaze cues to understand human intent during collaborative tasks. These contributions bridge computer vision, natural language, and robotics, with potential applications in assistive technology and smart glasses. Chen’s work is gaining traction for its practical approach to grounding abstract affordances in visual data, making her a notable voice in the next generation of interactive AI research.