-
End-to-End Automatic Image Cropping System
The proposed end-to-end automatic image cropping system is proposed to learn the relationship between the objects of interests and the areas with high aesthetic scores in an... -
Improving wildfire severity classification of deep learning u-nets from satelli...
Improving wildfire severity classification of deep learning u-nets from satellite images. -
Deep learning-based framework for cardiac function assessment in embryonic ze...
A deep learning-based framework for cardiac function assessment in embryonic zebrafish from heart beating videos. -
MNIST data set
The MNIST data set is a dataset used for testing the performance of the DisDF. -
ResNet-56 Dataset
The dataset used in the paper for hyper-parameter tuning using transient cloud resources. -
Physics-informed neural network solution of thermo-hydro-mechanical (THM) pro...
Physics-Informed Neural Networks (PINNs) have received increased interest for forward, inverse, and surrogate modeling of problems described by partial differential equations... -
MaskFlow: Object-Aware Motion Estimation
A novel motion estimation method that combines object-level representations and matching with a state of the art multi-scale DNN-based method. -
Neural Lattice Reduction
The dataset used in the paper is a randomly-generated dataset of lattices, where each lattice is represented by a basis of n vectors in R^n. -
Jet Constituents for Deep Neural Network Based Top Quark Tagging
A dataset for discriminating top-quark originated jets from jets originating from all other quark flavours and gluons -
Tangent Kernel Approach for Class Balanced Incremental Learning
The proposed method is a class-balanced incremental learning approach that aims to address both classes-balanced accuracy and overall classification accuracy. -
Parallel sentence extraction
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. -
Simulation Framework for Turbo Encoding and Decoding
The dataset used in this paper is a simulation framework for turbo encoding and decoding operations. It consists of four autoencoding problems: one for encoding and three for... -
Bigeometric Organization of Deep Nets
The dataset is used to demonstrate the bigeometric organization of deep nets. It contains hospital quality data from the Center for Medicare and Medicaid Services Hospital... -
Truss Design Study
A dataset of historical human design data used to train a deep learning framework to learn human design strategies and generate high performing designs. -
Embedding Deep Metric for Person Re-identification: A Study Against Large Vari...
Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is... -
Video Surveillance of Highway Traffic Events by Deep Learning Architectures
Video surveillance system able to detect traffic events in videos acquired by fixed cameras on highways. -
Mass Estimation from Images using Deep Neural Network and Sparse Ground Truth
The dataset used in the paper is a collection of images of a sugarcane elevator and running bamboo under controlled testing, with a total of 239 runs split into 60/20/20 -...
