320 datasets found

Image data provide unique information about political events, actors, and their interactions which are difficult to measure from or not available in text data.

The dataset used in the paper for testing the proposed squared curvature regularization approach.

The dataset used in this paper for computing 4th order 2D image moments using the Discrete Radon Transform.

Generating photo-realistic images from a text description is a challenging problem in computer vision. Previ- ous works have shown promising performance to generate synthetic...

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch

Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, focused in identifying the bounding boxes that contain the product being sold in...

The dataset used in this paper is a light field photography dataset using a hand-held plenoptic camera.

The dataset used in this paper is a shield fields dataset for modeling and capturing 3D occluders.

Open3D: A modern library for 3D data processing

3D object recognition dataset

3D object recognition dataset

The dataset used for the maze exploration task, containing a 9x9 maze with walls and reward locations.

A category-level shape estimation framework for densely cluttered objects

The MNIST dataset is a large dataset of handwritten digits, and the ImageNet dataset is a large dataset of images.

A novel MicroISP model designed specifically for edge devices, taking into account their computational and memory limitations.

A novel MicroISP model designed specifically for edge devices, taking into account their computational and memory limitations.

CIFAR-10-C and CIFAR-100-C are robustness benchmarks consisting of 19 corruptions types with five levels of severities.

The DecoyFMNIST dataset is an updated version of MNIST that is more complex and less overused in research.

The DecoyMNIST dataset is a variation of MNIST with decoy squares in the image corners, confounding the training data.

The Office-10 dataset is a more classic benchmark dataset from [17].