320 datasets found

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The MS COCO dataset is a large benchmark for image captioning, containing 328K images with 5 caption descriptions each.

The ImageNet dataset is a large-scale image database that contains over 14 million images, each labeled with one of 21,841 categories.

Hyperhuman dataset for 3D face rendering

The ImageNet21K dataset is used for training and evaluation of the proposed Circulant Channel-Specific (CCS) token-mixing MLP.

The dataset used in this paper is a collection of frames for video coding, with different Quantisation Parameters (QPs) and frame types.

The Omniglot dataset consists of 100 classes, each containing 20 images. Ten images were taken from each class for augmentation, and the rest were used as the test set. Each...

The Blender dataset consists of 8 synthetic 3D scenes, each with a hundred posed images of resolution 800 × 800.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used TinyImagenet dataset for pre-training the embedding functions.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used CIFAR-10, CIFAR-100, and STL-10 datasets for training and testing the...

The dataset used in the paper is a 3D mesh dataset, which is used for training and testing the Surface Networks model.

The dataset used in the paper Neural 3D Mesh Renderer. The dataset consists of 3D models of objects.

Large dataset for stereo matching, optical flow, and scene flow estimation

The Human Action Recognition dataset is used for human action recognition tasks.

The dataset used in the paper is Places, a large dataset of 400k pairs of images from the Places 205 dataset and corresponding spoken audio captions.

The MVG dataset, which contains 1,009 samples, each with five images of the same person wearing the same garment from five different views.

The proposed method for Multi-View Virtual Try-On (MV-VTON) task, which aims at using the frontal and back clothing to reconstruct the dressing results of a person from multiple...

The proposed method, dubbed Dynamic Hyperpixel Flow, learns to compose hypercolumn features on the fly by selecting a small number of relevant layers from a deep convolutional...

The dataset used in the paper is the ResNet-50 dataset, a convolutional neural network model.