Picture for Sunoh Kim

Sunoh Kim

Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection

Add code
Mar 29, 2025
Viaarxiv icon

Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding

Add code
Dec 27, 2023
Viaarxiv icon

Position-aware Location Regression Network for Temporal Video Grounding

Add code
Apr 12, 2022
Figure 1 for Position-aware Location Regression Network for Temporal Video Grounding
Figure 2 for Position-aware Location Regression Network for Temporal Video Grounding
Figure 3 for Position-aware Location Regression Network for Temporal Video Grounding
Figure 4 for Position-aware Location Regression Network for Temporal Video Grounding
Viaarxiv icon

Skeleton-based Action Recognition of People Handling Objects

Add code
Jan 21, 2019
Figure 1 for Skeleton-based Action Recognition of People Handling Objects
Figure 2 for Skeleton-based Action Recognition of People Handling Objects
Figure 3 for Skeleton-based Action Recognition of People Handling Objects
Figure 4 for Skeleton-based Action Recognition of People Handling Objects
Viaarxiv icon