Recently, an emerging light field imaging technology, which enables capturing full light information in a scene, has gained a lot of interest. To design, develop, implement, and test novel algorithms in light field image processing and compression, the availability of suitable light field image datasets is essential. In this paper, a publicly available light field image dataset is introduced an...

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set of transformations must be carefully designed, implemented, and tested for every new domain, limiting its re-use and generality. In this paper, we adopt a sim...

This paper introduces ASTD, an Arabic social sentiment analysis dataset gathered from Twitter. It consists of about 10,000 tweets which are classified as objective, subjective positive, subjective negative, and subjective mixed. We present the properties and the statistics of the dataset, and run experiments using standard partitioning of the dataset. Our experiments provide benchmark results f...

Appropriate datasets are required at all stages of object recognition research, including learning visual models of object and scene categories, detecting and localizing instances of these models in images, and evaluating the performance of recognition algorithms. Current datasets are lacking in several respects, and this paper discusses some of the lessons learned from existing efforts, as wel...

Purpose: Retinal image registration is a useful tool for medical professionals. However, evaluating the accuracy of these registrationmethods has not been consistently undertaken in the literature. To address this, a dataset comprised of retinal image pairs annotated with ground truth and an evaluation protocol for registration methods is proposed. Methods: The dataset is comprised of 134 retin...

Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce. A key limitation is data efficiency, with current state-of-the-art approaches requiring millions of training samples. A promising way to tackle this problem is t...

Until now, most existing researches on person re-identification aim at improving the recognition rate on single dataset setting. The training data and testing data of these methods are form the same source. Although they have obtained high recognition rate in experiments, they usually perform poorly in practical applications. In this paper, we focus on the cross dataset person re-identification...

In this project, we perform a text independent speaker identification experiment with a newly released data set, VoxCeleb (2017)[1], which consists of celebrity interview audio clips downloaded from Youtube. It’s a challenging data set in the sense that there are often multiple vocal sources in the same clip. A MFCC feature vector based Deep Neural Network (DNN) is used as our baseline. It is c...

Link discovery is the problem of linking entities between two or more datasets, based on some (possibly unknown) specification. A blocking scheme is a one-to-many mapping from entities to blocks. Blocking methods avoid O(n) comparisons by clustering entities into blocks, and limiting the evaluation of link specifications to entity pairs within blocks. Current link-discovery blocking methods exp...