Changan Chen

6

Papers

44

Total Citations

Papers (6)

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

F3Loc: Fusion and Filtering for Floorplan Localization

SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos

Self-Supervised Cross-View Correspondence with Predictive Cycle Consistency

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion

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