Kumar Ashutosh

8

Papers

71

Total Citations

Papers (8)

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

ExpertAF: Expert Actionable Feedback from Video

SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos

Detours for Navigating Instructional Videos

LLMs can see and hear without any training

FIction: 4D Future Interaction Prediction from Video

Learning Skill-Attributes for Transferable Assessment in Video

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