
BitMixer: Mixedprecision networks with runtime bitwidth selection
Mixedprecision networks allow for a variable bitwidth quantization for...
read it

Pretraining strategies and datasets for facial representation learning
What is the best way to learn a universal face representation? Recent wo...
read it

Improving memory banks for unsupervised learning with large minibatch, consistency and hard negative mining
An important component of unsupervised learning by instancebased discri...
read it

Semisupervised Facial Action Unit Intensity Estimation with Contrastive Learning
This paper tackles the challenging problem of estimating the intensity o...
read it

HighCapacity Expert Binary Networks
Network binarization is a promising hardwareaware direction for creatin...
read it

A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation
Action Units (AUs) are geometricallybased atomic facial muscle movement...
read it

Training Binary Neural Networks with RealtoBinary Convolutions
This paper shows how to train binary networks to within a few percent po...
read it

Knowledge distillation via adaptive instance normalization
This paper addresses the problem of model compression via knowledge dist...
read it

BATS: Binary ArchitecTure Search
This paper proposes Binary ArchitecTure Search (BATS), a framework that ...
read it

Toward fast and accurate human pose estimation via softgated skip connections
This paper is on highly accurate and highly efficient human pose estimat...
read it

Towards Poseinvariant LipReading
Lipreading models have been significantly improved recently thanks to p...
read it

XNORNet++: Improved Binary Neural Networks
This paper proposes an improved training algorithm for binary neural net...
read it

Efficient NDimensional Convolutions via HigherOrder Factorization
With the unprecedented success of deep convolutional neural networks cam...
read it

Matrix and tensor decompositions for training binary neural networks
This paper is on improving the training of binary neural networks in whi...
read it

Incremental multidomain learning with network latent tensor factorization
The prominence of deep learning, large amount of annotated data and incr...
read it

Improved training of binary networks for human pose estimation and image recognition
Big neural networks trained on large datasets have advanced the stateof...
read it

TNet: Parametrizing Fully Convolutional Nets with a Single HighOrder Tensor
Recent findings indicate that overparametrization, while crucial for su...
read it

Hierarchical binary CNNs for landmark localization with limited resources
Our goal is to design architectures that retain the groundbreaking perfo...
read it

To learn image superresolution, use a GAN to learn how to do image degradation first
This paper is on image and face superresolution. The vast majority of p...
read it

SuperFAN: Integrated facial landmark localization and superresolution of realworld low resolution faces in arbitrary poses with GANs
This paper addresses two challenging tasks: improving the quality of rea...
read it

Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
3D face reconstruction is a fundamental Computer Vision problem of extra...
read it

How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
This paper investigates how far a very deep neural network is from attai...
read it

Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources
Our goal is to design architectures that retain the groundbreaking perfo...
read it

Twostage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge
This paper describes our submission to the 1st 3D Face Alignment in the ...
read it

Human pose estimation via Convolutional Part Heatmap Regression
This paper is on human pose estimation using Convolutional Neural Networ...
read it
Adrian Bulat
is this you? claim profile