Tushar Nagarajan

23

Papers

141

Total Citations

Papers (23)

Video ReCap: Recursive Captioning of Hour-Long Videos

AMEGO: Active Memory from long EGOcentric videos

ExpertAF: Expert Actionable Feedback from Video

Step Differences in Instructional Video

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

Detours for Navigating Instructional Videos

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

EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception

Grounded Human-Object Interaction Hotspots From Video

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

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

VITED: Video Temporal Evidence Distillation

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

BlockDrop: Dynamic Inference Paths in Residual Networks

Ego-Topo: Environment Affordances From Egocentric Video

Ego-Exo: Transferring Visual Representations From Third-Person to First-Person Videos

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Learning Affordance Landscapes for Interaction Exploration in 3D Environments

Shaping embodied agent behavior with activity-context priors from egocentric video

EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities

HT-Step: Aligning Instructional Articles with How-To Videos

EgoEnv: Human-centric environment representations from egocentric video