Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities

NAACL 2019 2 code implementations

Scholars in inter-disciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora.

ACTIVE LEARNING NAMED ENTITY RECOGNITION

Software Framework for Topic Modelling with Large Corpora

Workshop On New Challenges For NLP Frameworks 2010 1 code implementation

Large corpora are ubiquitous in today’s world and memory quickly becomes the limiting factor in practical applications of the Vector Space Model (VSM).

TOPIC MODELS

Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network

Nature Medicine 2019 2 code implementations

With specificity fixed at the average specificity achieved by cardiologists, the sensitivity of the DNN exceeded the average cardiologist sensitivity for all rhythm classes.

ARRHYTHMIA DETECTION

FPGA Implementation of Convolutional Neural Networks with Fixed-Point Calculations

29 Aug 20183 code implementations

We propose a number of methods for neural network architecture design to improve the performance with fixed-point calculations.

Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization

22 Nov 20181 code implementation

Parametric generative deep models are state-of-the-art for photo and non-photo realistic image stylization.

IMAGE STYLIZATION

Camera Lens Super-Resolution

CVPR 2019 1 code implementation

Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling.

IMAGE SUPER-RESOLUTION

Trinity of Pixel Enhancement: a Joint Solution for Demosaicking, Denoising and Super-Resolution

7 May 20192 code implementations

Despite the recent improvement of learning-based image processing methods in image quality, there lacks enough analysis into their interactions and characteristics under a realistic setting of the mixture problem of demosaicing, denoising and SR.

DEMOSAICKING DENOISING SUPER RESOLUTION

Annotation as a New Paradigm in Research Archiving

7 Oct 20141 code implementation

The second one (DTHB) is a multi-year effort to express the linguistic features of the Hebrew bible in a text database, which is still growing in detail and sophistication.

Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit

CVPR 2016 1 code implementation

Subspace clustering methods based on $\ell_1$, $\ell_2$ or nuclear norm regularization have become very popular due to their simplicity, theoretical guarantees and empirical success.