Ehsan Elhamifar

13

Papers

40

Total Citations

Papers (13)

Learning to Predict Activity Progress by Self-Supervised Video Alignment

Two-Stage Active Learning for Efficient Temporal Action Segmentation

MOSCATO: Predicting Multiple Object State Change Through Actions

Understanding Multi-Task Activities from Single-Task Videos

DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos

Multi-Modal Few-Shot Temporal Action Segmentation

Error Recognition in Procedural Videos using Generalized Task Graph

FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation

Error Detection in Egocentric Procedural Task Videos

Compositional Targeted Multi-Label Universal Perturbations

Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos

Learning to Segment Referred Objects from Narrated Egocentric Videos

Semantic-Aware Multi-Label Adversarial Attacks