Search Results for author:
Found 13 papers, 8 papers with code
GaitContour: Efficient Gait Recognition based on a Contour-Pose Representation
Gait recognition holds the promise to robustly identify subjects based on walking patterns instead of appearance information.
DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
Diffusion models have advanced generative AI significantly in terms of editing and creating naturalistic images.
Dual Prompt Tuning for Domain-Aware Federated Learning
Federated learning is a distributed machine learning paradigm that allows multiple clients to collaboratively train a shared model with their local data.
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.
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
STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos
We address the problem of extracting key steps from unlabeled procedural videos, motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training and performance.
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.
Unfolding a blurred image
This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.
Max-Margin Contrastive Learning
Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence.
Ranked #108 on
Self-Supervised Image Classification
on ImageNet
Object-Aware Cropping for Self-Supervised Learning
This assumption is mostly satisfied in datasets such as ImageNet where there is a large, centered object, which is highly likely to be present in random crops of the full image.
Learning Visual Representations for Transfer Learning by Suppressing Texture
Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information.
Ranked #19 on
Object Detection
on PASCAL VOC 2007
Pose And Joint-Aware Action Recognition
Unlike other modalities, constellation of joints and their motion generate models with succinct human motion information for activity recognition.
Ranked #1 on
Action Recognition
on Mimetics
Bringing Alive Blurred Moments
This network extracts embedded motion information from the blurred image to generate a sharp video in conjunction with the trained recurrent video decoder.
Ranked #36 on
Image Deblurring
on GoPro
(using extra training data)
