9 datasets found

Formats: JSON Tags: Image Description

Filter Results

  • Multi30k

    The Multi30k dataset is an extension of the Flickr30k dataset, containing 29,000 train images, 1,014 validation images and 1,000 test images. Each image is accompanied with six...

  • COCO Captions and Localized Narratives

    The dataset used in the paper is COCO captions and Localized Narratives, which are used to generate image descriptions.

  • VQA-CP v2 and VQA 2.0

    The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering.

  • VQA 2.0

    The VQA 2.0 dataset is used for visual question answering task. It consists of three sets with a train set containing 83k images and 444k questions, a validation set containing...

  • Flickr30k

    The Flickr30k dataset is widely utilized for image caption and image-text retrieval tasks, providing a substantial collection of images with associated captions.

  • MS-COCO

    Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

  • Visual Story-Telling dataset (VIST)

    Visual Story-Telling dataset (VIST) is the only publicly accessible dataset for storytelling problems. It comprises 210,819 distinct images that can be found in 10,117 different...

  • COCO

    Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

  • MSCOCO

    Human Pose Estimation (HPE) aims to estimate the position of each joint point of the human body in a given image. HPE tasks support a wide range of downstream tasks such as...
You can also access this registry using the API (see API Docs).