Search Results for author:
Found 8 papers, 4 papers with code
MV2MAE: Multi-View Video Masked Autoencoders
We report state-of-the-art results on the NTU-60, NTU-120 and ETRI datasets, as well as in the transfer learning setting on NUCLA, PKU-MMD-II and ROCOG-v2 datasets, demonstrating the robustness of our approach.
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition.
DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
Diffusion models have advanced generative AI significantly in terms of editing and creating naturalistic images.
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
In this work, we propose a new contrastive learning approach to train models for skeleton-based action recognition without labels.
Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
The dataset is composed of both real and synthetic videos from seven gesture classes, and is intended to support the study of synthetic-to-real domain shift for video-based action recognition.
Multi-View Action Recognition Using Contrastive Learning
We present a supervised contrastive learning framework to learn a feature embedding robust to changes in viewpoint, by effectively leveraging multi-view data.
Ranked #11 on
Action Recognition
on NTU RGB+D 120
Cap2Aug: Caption guided Image to Image data Augmentation
We generate captions from the limited training images and using these captions edit the training images using an image-to-image stable diffusion model to generate semantically meaningful augmentations.
Improved Modeling of 3D Shapes with Multi-view Depth Maps
Our simple encoder-decoder framework, comprised of a novel identity encoder and class-conditional viewpoint generator, generates 3D consistent depth maps.
