Domain generalization aims to learn a model with good generalization abi...
Unobtrusive monitoring of distances between people indoors is a useful t...
Reliable and cost-effective counting of people in large indoor spaces is...
Domain generalization (DG) is a branch of transfer learning that aims to...
Person re-identification (PRID) from side-mounted rectilinear-lens camer...
Unsupervised contrastive learning (UCL) is a self-supervised learning
te...
In this paper, we propose a novel domain generalization (DG) framework b...
Invariance principle-based methods, for example, Invariant Risk Minimiza...
We study the problem of designing hard negative sampling distributions f...
Random walk based node embedding algorithms learn vector representations...
For the Domain Generalization (DG) problem where the hypotheses are comp...
Background subtraction (BGS) is a fundamental video processing task whic...
When journalists cover a news story, they can cover the story from multi...
Recent methods for people detection in overhead, fisheye images either u...
Smart buildings use occupancy sensing for various tasks ranging from
ene...
We present a novel variational generative adversarial network (VGAN) bas...
Background subtraction is a basic task in computer vision and video
proc...
We propose a cyclically-trained adversarial network to learn mappings fr...
Due to concerns about human error in crowdsourcing, it is standard pract...
Real-time, online-editing web apps provide free and convenient services ...
Reliable facial expression recognition plays a critical role in human-ma...
We propose a data-driven framework for optimizing privacy-preserving dat...
Neural node embeddings have recently emerged as a powerful representatio...
Deep convolutional neural networks (ConvNets) have been recently shown t...
We develop necessary and sufficient conditions and a novel provably
cons...
We propose a novel parameterized family of Mixed Membership Mallows Mode...
We propose a topic modeling approach to the prediction of preferences in...
We present algorithms for topic modeling based on the geometry of
cross-...
We study high-dimensional asymptotic performance limits of binary superv...
A new geometrically-motivated algorithm for nonnegative matrix factoriza...