Picture for Sunil Hwang

Sunil Hwang

Efficient Video Representation Learning via Masked Video Modeling with Motion-centric Token Selection

Add code
Nov 19, 2022
Figure 1 for Efficient Video Representation Learning via Masked Video Modeling with Motion-centric Token Selection
Figure 2 for Efficient Video Representation Learning via Masked Video Modeling with Motion-centric Token Selection
Figure 3 for Efficient Video Representation Learning via Masked Video Modeling with Motion-centric Token Selection
Figure 4 for Efficient Video Representation Learning via Masked Video Modeling with Motion-centric Token Selection
Viaarxiv icon

Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation

Jun 20, 2022
Figure 1 for Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
Figure 2 for Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
Figure 3 for Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
Figure 4 for Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation
Viaarxiv icon