1,082 datasets found

Graph Edit Distance as a quadratic assignment problem.

We use the preprocessed binarized MNIST dataset from [49] which has a split of 50k/10k/10k.

The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions.

The dataset used in the paper is not explicitly described. However, it is mentioned that the authors used various benchmarks such as ImageNet, ImageNet ReaL, ImageNet V2, etc.

VideoAttentionTarget is a video-based gaze target dataset comprising 71,666 frames from 1,331 clips.

GazeFollow is a large-scale dataset consisting of 122,143 images with 130,339 annotations on head-target instances.

Gaze target detection aims to directly associate individuals and their gaze targets within a single image or across multiple video frames.

The dataset used in the paper is the AlexNet dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class.

The authors propose a method for self-supervised representation learning using knowledge distillation and vision transformers.

The authors propose a method for zero-shot classification that leverages conditional density estimates from text-to-image diffusion models.

Diffusion models have recently emerged as the state-of-the-art of generative modeling, demonstrating remarkable results in image synthesis and across other modalities.

Diffusion Models are popular generative modeling methods in various vision tasks, attracting significant attention. They can be considered a unique instance of self-supervised...

The dataset used in the paper is the NuScenes dataset, which contains LiDAR point clouds and corresponding semantic annotations.

The dataset used in the paper is the ImageNet and MS COCO benchmarks.

A real dataset of depth images of fabrics, with mechanical ground truth parameters, used to test and evaluate a method for estimating fabric mechanics from depth images.

A synthetic dataset of depth images of fabrics, with mechanical ground truth parameters, used to train and evaluate a method for estimating fabric mechanics from depth images.

The dataset used for training and testing the direct regression model, sparse correspondence model, and dense correspondence model.

The dataset used for learning-based methods for online eye-in-hand camera calibration from a single RGB image.

ScanRefer is a dataset of 51,583 referring descriptions of 11,046 objects from 800 ScanNet scenes.

Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime.