-
Fashion-MNIST, CIFAR-10, and GTSRB datasets
The Fashion-MNIST, CIFAR-10, and GTSRB datasets were used to evaluate differentiable logics for learning systems. -
Geometry Constrained Weakly Supervised Object Localization
A geometry constrained network for weakly supervised object localization. -
nuScene Dataset
The nuScene dataset contains images and annotations of objects in the scene. -
Topological Convolutional Neural Networks
The dataset used in the paper for 2D image classification, including MNIST, SVHN, USPS, and CIFAR-10 datasets. -
Habitat-Matterport3D Research Dataset
The Habitat-Matterport3D Research Dataset is used as a test environment. -
Habitat-Sim and Habitat-Matterport3D Research Dataset
The Habitat-Sim and the Habitat-Matterport3D Research Dataset are used as training and deployment (test) environments. -
Social distancing surveillance application
A computer vision-based AI-assisted solution to aid compliance with social distancing norms. -
MLPerf Benchmark Dataset
The dataset used in this paper is the MLPerf benchmark dataset. -
KITTI Odometry
The dataset used in the paper is a large-scale point cloud compression framework, which can organize sparse and un-structured point clouds in a memory-efficient way. -
CIFAR-10, CIFAR-100, CINIC-10, SVHN, and ImageNet
The dataset used for the experiments on CIFAR-10, CIFAR-100, CINIC-10, SVHN, and ImageNet. -
DrivingStereo
A real-world stereo dataset containing both indoor and outdoor environments via robot teleoperation. -
Synthetic Training Dataset for Real-time Neural Woven Fabric Rendering
The dataset contains 81 plain materials, 192 twill materials, and 192 satin materials. -
Tiny-ImageNet, CIFAR100, and CIFAR10
The authors used Tiny-ImageNet, CIFAR100, and CIFAR10 datasets for their experiments. -
Scale Steerable Filters for Locally Scale-Invariant Convolutional Neural Netw...
The proposed scale-steerable CNN framework is validated on the MNIST-Scale and FMNIST-Scale datasets, which contain global scale variations. Additionally, a synthesized dataset,... -
Edge-Preserving Image Smoothing Dataset
A dataset for edge-preserving image smoothing, containing 500 training and testing images with a number of representative visual object categories. -
Edge-Preserving Image Smoothing Benchmark
A benchmark for edge-preserving image smoothing for the purpose of quantitative performance evaluation and further advancing the state-of-the-art. -
NED Distortion Dataset
The dataset used for training and testing the Neural Distortion Field (NDF) model for spatial calibration of wide Field-of-View Near-Eye Displays (NEDs). -
PASCAL VOC2012 Dataset
The PASCAL VOC2012 dataset is a benchmark for object detection, containing 1464 images with corresponding labeled object instances for 20 classes.
