1,082 datasets found

CIFAR-10 and CIFAR-100 are standard vision datasets with 50,000 training images across 10 and 100 classes, respectively.

MIT-67 is a dataset of 67 indoor scenes, CUB-2011 is a dataset of 200 bird species, Caltech-101 is a dataset of 101 objects, and DTD is a dataset of 47 textures.

The dataset used in the paper is a set of visual recognition tasks, spanning both the data-abundant and data-limited regimes.

Convolutional Neural Network (CNN) has demonstrated its success in plentiful computer vision application, but typically accompanies high computation cost and numerous redundant...

A new automatic algorithm for the diagnosis and grading of sacroiliitis in CT scans as incidental findings, for patients who underwent lower back or abdomen CT scanning as part...

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the CLIP model and the Comics, Paintings, and ChestX datasets.

The proposed TransDepth framework for pixel-wise prediction problems involving continuous labels.

The 3DMatch [26] is a well-known indoor registration dataset of 62 scenes captured by RGBD sensor.

The InterHand2.6M dataset contains 366K training samples, 110K validation samples, and 261K test samples. It is the only interacting two-hand dataset with dense shape annotations.

CelebA: A Large-Scale Dataset and Network for Face Attribute Estimation

Deep learning face attributes in the wild

Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models

Table tennis stroke detection and recognition using ball trajectory data

The KITTI odometry dataset is a benchmark for evaluating visual odometry and other computer vision tasks. It contains a large collection of images and corresponding ground-truth...

A dataset for semantic object classes in video.

The dataset used in this paper is a collection of clean and adversarial examples for deep neural networks.

The dataset used in the paper is the YFCC-100M dataset, a large-scale image dataset.

A synthetic dataset of shoes for training and testing the proposed method.

A unified object-centric implicit representation that can be used for RGB and depth novel view rendering, 3D reconstruction, and proposing stable grasps.

The LUNA dataset is a public benchmark widely used for direct comparison between various methods proposed in the literature.