Sagnik Majumder

4

Papers

11

Total Citations

Papers (4)

Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos

Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos

Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos

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