research
∙
05/19/2023
Enhancing Transformer Backbone for Egocentric Video Action Segmentation
Egocentric temporal action segmentation in videos is a crucial task in c...
share
research
∙
05/02/2023
Cross-view Action Recognition via Contrastive View-invariant Representation
Cross view action recognition (CVAR) seeks to recognize a human action w...
research
∙
02/09/2023
Geometry of Score Based Generative Models
In this work, we look at Score-based generative models (also called diff...
research
∙
02/05/2023
Divide and Compose with Score Based Generative Models
While score based generative models, or diffusion models, have found suc...
research
∙
11/08/2021
Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection
There are limited works showing the efficacy of unsupervised Out-of-Dist...
research
∙
10/01/2021
Self-Supervised Decomposition, Disentanglement and Prediction of Video Sequences while Interpreting Dynamics: A Koopman Perspective
Human interpretation of the world encompasses the use of symbols to cate...
research
∙
07/30/2020
Key Frame Proposal Network for Efficient Pose Estimation in Videos
Human pose estimation in video relies on local information by either est...
research
∙
06/23/2020
Learning Disentangled Representations of Video with Missing Data
Missing data poses significant challenges while learning representations...
research
∙
11/18/2019
Towards Visually Explaining Variational Autoencoders
Recent advances in Convolutional Neural Network (CNN) model interpretabi...
research
∙
03/20/2018
DYAN: A Dynamical Atoms Network for Video Prediction
The ability to anticipate the future is essential when making real time ...
research
∙
02/20/2018
MoNet: Moments Embedding Network
Bilinear pooling has been recently proposed as a feature encoding layer,...
research
∙
09/20/2017
Multi-camera Multi-Object Tracking
In this paper, we propose a pipeline for multi-target visual tracking un...
research
∙
05/31/2016
A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets
Person re-identification (re-id) is a critical problem in video analytic...
research
∙
04/01/2016
Person Re-identification in Appearance Impaired Scenarios
Person re-identification is critical in surveillance applications. Curre...
research
∙
04/03/2015