research
∙
06/15/2023
Robustness Analysis on Foundational Segmentation Models
Due to the increase in computational resources and accessibility of data...
share
research
∙
07/16/2022
SVGraph: Learning Semantic Graphs from Instructional Videos
In this work, we focus on generating graphical representations of noisy,...
research
∙
07/05/2022
Multi-modal Robustness Analysis Against Language and Visual Perturbations
Joint visual and language modeling on large-scale datasets has recently ...
research
∙
06/18/2022
Self-Supervised Learning for Videos: A Survey
The remarkable success of deep learning in various domains relies on the...
research
∙
10/21/2021
LARNet: Latent Action Representation for Human Action Synthesis
We present LARNet, a novel end-to-end approach for generating human acti...
research
∙
10/15/2021
Pose-guided Generative Adversarial Net for Novel View Action Synthesis
We focus on the problem of novel-view human action synthesis. Given an a...
research
∙
07/24/2021
TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos
This paper summarizes the TinyAction challenge which was organized in Ac...
research
∙
06/07/2021
Novel View Video Prediction Using a Dual Representation
We address the problem of novel view video prediction; given a set of in...
research
∙
05/22/2021
PLM: Partial Label Masking for Imbalanced Multi-label Classification
Neural networks trained on real-world datasets with long-tailed label di...
research
∙
04/30/2021
Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities
Action recognition and detection in the context of long untrimmed video ...
research
∙
01/15/2021
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
The recent research in semi-supervised learning (SSL) is mostly dominate...
research
∙
11/22/2020
We don't Need Thousand Proposals Single Shot Actor-Action Detection in Videos
We propose SSA2D, a simple yet effective end-to-end deep network for act...
research
∙
09/01/2020
View-invariant action recognition
Human action recognition is an important problem in computer vision. It ...
research
∙
07/14/2020
TinyVIRAT: Low-resolution Video Action Recognition
The existing research in action recognition is mostly focused on high-qu...
research
∙
09/30/2019
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
In this work we propose a capsule-based approach for semi-supervised vid...
research
∙
12/02/2018
Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries
In this paper, we propose an end-to-end capsule network for pixel level ...
research
∙
11/26/2018
Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
The recent success in deep learning has lead to various effective repres...
research
∙
05/21/2018