DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks

ICCV 2017 3 code implementations

Despite a rapid rise in the quality of built-in smartphone cameras, their physical limitations - small sensor size, compact lenses and the lack of specific hardware, - impede them to achieve the quality results of DSLR cameras.

Medical Concept Representation Learning from Electronic Health Records and its Application on Heart Failure Prediction

11 Feb 20161 code implementation

Objective: To transform heterogeneous clinical data from electronic health records into clinically meaningful constructed features using data driven method that rely, in part, on temporal relations among data.

REGRESSION REPRESENTATION LEARNING

Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex

6 Jun 20181 code implementation

We show that one cause for such success is due to the fact that the multi-branch architecture is less non-convex in terms of duality gap.

Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization

ICCV 2017 1 code implementation

We present a robust algorithm for personalizing a sphere-mesh tracking model to a user from a collection of depth measurements.

CALIBRATION

Iterative Inversion of Deformation Vector Fields with Feedback Control

27 Oct 20161 code implementation

Conclusion: Our analysis captures properties of DVF data associated with clinical CT images, and provides new understanding of iterative DVF inversion algorithms with a simple residual feedback control.

IMAGE REGISTRATION

Unsupervised Representation Learning of Structured Radio Communication Signals

24 Apr 20161 code implementation

We explore unsupervised representation learning of radio communication signals in raw sampled time series representation.

TIME SERIES UNSUPERVISED REPRESENTATION LEARNING

Separating common (global and local) and distinct variation in multiple mixed types data sets

17 Feb 20192 code implementations

A Majorization-Minimization based algorithm is derived to fit the proposed model.

MODEL SELECTION

A fatal point concept and a low-sensitivity quantitative measure for traffic safety analytics

28 Nov 2017no code implementations

The variability of the clusters generated by clustering techniques in the domain of latitude and longitude variables of fatal crash data are significantly unpredictable.

Cannot find the paper you are looking for? You can Submit a new open access paper.