Picture for Yogesh Singh Rawat

Yogesh Singh Rawat

HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding

Add code
Mar 11, 2025
Viaarxiv icon

Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

Add code
Jan 28, 2025
Viaarxiv icon

Stable Mean Teacher for Semi-supervised Video Action Detection

Add code
Dec 10, 2024
Viaarxiv icon

Asynchronous Perception Machine For Efficient Test-Time-Training

Add code
Oct 27, 2024
Viaarxiv icon

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

Add code
Oct 25, 2024
Figure 1 for On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
Figure 2 for On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
Figure 3 for On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
Figure 4 for On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
Viaarxiv icon

Activity-Biometrics: Person Identification from Daily Activities

Add code
Mar 26, 2024
Viaarxiv icon

Semi-supervised Active Learning for Video Action Detection

Add code
Dec 12, 2023
Figure 1 for Semi-supervised Active Learning for Video Action Detection
Figure 2 for Semi-supervised Active Learning for Video Action Detection
Figure 3 for Semi-supervised Active Learning for Video Action Detection
Figure 4 for Semi-supervised Active Learning for Video Action Detection
Viaarxiv icon

PRAT: PRofiling Adversarial aTtacks

Add code
Sep 20, 2023
Viaarxiv icon

Efficiently Robustify Pre-trained Models

Add code
Sep 14, 2023
Viaarxiv icon

Benchmarking self-supervised video representation learning

Add code
Jun 09, 2023
Viaarxiv icon