24,167 datasets found

Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories.

A dataset of textual entailment tasks, used for evaluating the ability of language models to understand relationships between texts.

A dataset for video rain streak removal, constructed using multiscale convolutional sparse coding.

A dataset for rain streak removal from light field images, constructed using 4D convolution and multi-scale Gaussian process.

A rainy scene dataset for rain streak removal, constructed using real-world video data.

A comprehensive and diverse multi-view rainy image dataset for deraining tasks, constructed using Maya software.

The YouTube-VOS 2018 dataset is a large-scale benchmark for video object segmentation.

Semi-supervised video object segmentation (VOS) aims to track the designated objects present in the initial frame of a video at the pixel level.

A dataset for generative object insertion in 3D scenes

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used DeiT and ViT models on ImageNet-1k and CIFAR-100 datasets.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used DeiT and ViT models on ImageNet-1k and CIFAR-100 datasets.

A novel dataset of laryngeal endoscopic images with ground truth segmentation maps for comparative study on CNN-based semantic segmentation.

Face swapping framework that generates a face swap latent code of a given generator.

The dataset used in the paper is a collection of spherical panoramas for indoor scene understanding tasks.

The Stanford 2D-3D dataset contains 552 cuboid room layouts labeled by Zou et al.

The dataset used for training and evaluation of the proposed LGT-Net model for 3D room layout estimation.

The ClearPose dataset consists of 63 objects arranged in numerous configurations.

The ClearPose Transparent Object Depth Completion dataset consists of 63 objects arranged in numerous configurations.

The dataset used in the paper is a collection of small images, each representing a patch of a jigsaw puzzle. The patches are of the same size and orientation, and the goal is to...

The dataset used in the paper is the ZINC dataset, which is a large dataset of molecules.