Ehsan Elhamifar

32

Papers

119

Total Citations

Papers (32)

High-Rank Matrix Completion and Clustering under Self-Expressive Models

Learning to Predict Activity Progress by Self-Supervised Video Alignment

Subset Selection and Summarization in Sequential Data

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

Online Summarization via Submodular and Convex Optimization

Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention

Interactive Multi-Label CNN Learning With Partial Labels

Introvert: Human Trajectory Prediction via Conditional 3D Attention

Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment

Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling

Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos

Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency

Unsupervised Procedure Learning via Joint Dynamic Summarization

Weakly-Supervised Action Segmentation and Alignment via Transcript-Aware Union-of-Subspaces Learning

Interaction Compass: Multi-Label Zero-Shot Learning of Human-Object Interactions via Spatial Relations

Self-Supervised Multi-Task Procedure Learning from Instructional Videos

Zero-Shot Attribute Attacks on Fine-Grained Recognition Models

A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning

Compositional Targeted Multi-Label Universal Perturbations

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

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

Deep Supervised Summarization: Algorithm and Application to Learning Instructions

Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition

Sequential Facility Location: Approximate Submodularity and Greedy Algorithm