74 datasets found

The Tecnick dataset is a dataset of 10 images, each with a size of 512x512 pixels.

The dataset used in this paper is the CIFAR10 dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class.

A slot value might be provided segment by segment over multiple-turn interactions in a dialog, especially for some important information such as phone numbers and names.

A large-scale, long-term, person re-ID dataset, called Celeb-reID, was built in 2019.

A dataset for video understanding, containing images and videos.

A dataset for video understanding, containing images and videos.

The dataset used in the paper is the OpenImage dataset.

COCO Stuff dataset is an extension of the COCO dataset, 164,000 images covering 171 classes are annotated with segmentation masks.

The dataset used for the experiments of the paper "CORE-PERIPHERY PRINCIPLE GUIDED REDISIGN OF SELF-ATTENTION IN TRANSFORMERS"

The dataset used in the paper is the Kodak PhotoCD dataset, which contains twenty-four 768 × 512 images.

The dataset is a collection of 256x256 pixel images.

The dataset consists of a significant collection of 60,000 facial expression images, categorized into eight different classes, including neutral, happy, angry, sad, fear,...

The dataset used in the paper is a wide domain image dataset, and the authors propose a weakly semi-supervised method for disentangling using both labeled and unlabeled data.

The dataset used in the paper is a wide domain image dataset, and the authors propose a weakly semi-supervised method for disentangling using both labeled and unlabeled data.

The dataset used in the paper is a wide domain image dataset, and the authors propose a weakly semi-supervised method for disentangling using both labeled and unlabeled data.

The dataset used in the paper is a wide domain image dataset, and the authors propose a weakly semi-supervised method for disentangling using both labeled and unlabeled data.

The dataset used in the paper is a wide domain image dataset, and the authors propose a weakly semi-supervised method for disentangling using both labeled and unlabeled data.

The proposed system is composed of three neural networks (NN): an auto-regressive module (ARM) fψ, an upsampler fυ and a synthesis fθ.

The dataset used in the paper is a set of sequential vision-and-language tasks, where each task consists of an image and a text input.

A large dataset for object detection, containing 118k training images and 5k validation images.