
A Meanfield Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Training deep neural networks with stochastic gradient descent (SGD) can...
read it

Machine Learning from a Continuous Viewpoint
We present a continuous formulation of machine learning, as a problem in...
read it

A Comparative Analysis of the Optimization and Generalization Property of Twolayer Neural Network and Random Feature Models Under Gradient Descent Dynamics
A fairly comprehensive analysis is presented for the gradient descent dy...
read it

Unsupervised Deep Tracking
We propose an unsupervised visual tracking method in this paper. Differe...
read it

See More, Know More: Unsupervised Video Object Segmentation with CoAttention Siamese Networks
We introduce a novel network, called COattention Siamese Network (COSNe...
read it

Analysis of the Gradient Descent Algorithm for a Deep Neural Network Model with Skipconnections
The behavior of the gradient descent (GD) algorithm is analyzed for a de...
read it

DepthAware Video Frame Interpolation
Video frame interpolation aims to synthesize nonexistent frames inbetwe...
read it

On the Generalization Properties of Minimumnorm Solutions for Overparameterized Neural Network Models
We study the generalization properties of minimumnorm solutions for thr...
read it

Deep Image Deraining Via Intrinsic Rainy Image Priors and Multiscale Auxiliary Decoding
Different rain models and novel network structures have been proposed to...
read it

EDDI: Efficient Dynamic Discovery of HighValue Information with Partial VAE
Making decisions requires information relevant to the task at hand. Many...
read it

A Priori Estimates of the Population Risk for Residual Networks
Optimal a priori estimates are derived for the population risk of a regu...
read it

Deep Attentive Tracking via Reciprocative Learning
Visual attention, derived from cognitive neuroscience, facilitates human...
read it

Deep Single Image Deraining Via Estimating Transmission and Atmospheric Light in rainy Scenes
Rain removal in images/videos is still an important task in computer vis...
read it

RealTime Correlation Tracking via Joint Model Compression and Transfer
Correlation filters (CF) have received considerable attention in visual ...
read it

Barron Spaces and the Compositional Function Spaces for Neural Network Models
One of the key issues in the analysis of machine learning models is to i...
read it

Deep Extreme Feature Extraction: New MVA Method for Searching Particles in High Energy Physics
In this paper, we present Deep Extreme Feature Extraction (DEFE), a new ...
read it

Robust Visual Tracking via Hierarchical Convolutional Features
Visual tracking is challenging as target objects often undergo significa...
read it

Adaptive Correlation Filters with LongTerm and ShortTerm Memory for Object Tracking
Object tracking is challenging as target objects often undergo drastic a...
read it

Person ReIdentification via Recurrent Feature Aggregation
We address the person reidentification problem by effectively exploitin...
read it

Learning a NoReference Quality Metric for SingleImage SuperResolution
Numerous singleimage superresolution algorithms have been proposed in ...
read it

Visual Question Answering with MemoryAugmented Networks
This paper exploits a memoryaugmented neural network to predict accurat...
read it

VITAL: VIsual Tracking via Adversarial Learning
The trackingbydetection framework consists of two stages, i.e., drawin...
read it

Variational Implicit Processes
This paper introduces the variational implicit processes (VIPs), a Bayes...
read it

CREST: Convolutional Residual Learning for Visual Tracking
Discriminative correlation filters (DCFs) have been shown to perform sup...
read it

Joint Neural Entity Disambiguation with Output Space Search
In this paper, we present a novel model for entity disambiguation that c...
read it

Model Reduction with Memory and the Machine Learning of Dynamical Systems
The wellknown MoriZwanzig theory tells us that model reduction leads t...
read it

A Priori Estimates of the Generalization Error for Twolayer Neural Networks
New estimates for the generalization error are established for the twol...
read it

PersonJob Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning
PersonJob Fit is the process of matching the right talent for the right...
read it

TargetAware Deep Tracking
Existing deep trackers mainly use convolutional neural networks pretrai...
read it

Global Convergence of Gradient Descent for Deep Linear Residual Networks
We analyze the global convergence of gradient descent for deep linear re...
read it
Chao Ma
is this you? claim profile