Picture for Ketul Shah

Ketul Shah

An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos

Add code
Oct 03, 2024
Viaarxiv icon

MV2MAE: Multi-View Video Masked Autoencoders

Add code
Jan 29, 2024
Viaarxiv icon

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

Add code
Dec 06, 2023
Viaarxiv icon

DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics

Add code
Nov 16, 2023
Viaarxiv icon

HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions

Add code
Apr 01, 2023
Viaarxiv icon

Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances

Add code
Mar 17, 2023
Viaarxiv icon

DiffAlign : Few-shot learning using diffusion based synthesis and alignment

Add code
Dec 11, 2022
Viaarxiv icon

Improved Modeling of 3D Shapes with Multi-view Depth Maps

Add code
Sep 07, 2020
Figure 1 for Improved Modeling of 3D Shapes with Multi-view Depth Maps
Figure 2 for Improved Modeling of 3D Shapes with Multi-view Depth Maps
Figure 3 for Improved Modeling of 3D Shapes with Multi-view Depth Maps
Figure 4 for Improved Modeling of 3D Shapes with Multi-view Depth Maps
Viaarxiv icon

Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor

Add code
Oct 25, 2018
Figure 1 for Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor
Figure 2 for Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor
Figure 3 for Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor
Figure 4 for Photorealistic Image Reconstruction from Hybrid Intensity and Event based Sensor
Viaarxiv icon