Dima Damen

8

Papers

48

Total Citations

Papers (8)

HD-EPIC: A Highly-Detailed Egocentric Video Dataset

Learning from One Continuous Video Stream

Learning from Streaming Video with Orthogonal Gradients

TIM: A Time Interval Machine for Audio-Visual Action Recognition

GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos

Context-Aware Multimodal Pretraining

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

ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions