Zihui Xue

7

Papers

70

Total Citations

Papers (7)

Learning Object State Changes in Videos: An Open-World Perspective

Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos

Detours for Navigating Instructional Videos

Progress-Aware Video Frame Captioning

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning

Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives