15 datasets found

The VizWiz-VQA dataset is a large-scale visual question answering dataset that consists of 4,000 images with 10 crowd-worker answers each.

The TallyQA dataset is a large-scale open-ended visual counting dataset, which is well-suited to study statistical shortcuts.

The High Quality Image Text Pairs (HQITP-134M) dataset consists of 134 million diverse and high-quality images paired with descriptive captions and titles.

The OK-VQA dataset is a visual question answering benchmark requiring external knowledge.

The Winoground dataset consists of 400 items, each containing two image-caption pairs (I0, C0), (I1, C1).

The VQA dataset is a large-scale visual question answering dataset that consists of pairs of images that require natural language answers.

The GQA dataset is a visual question answering dataset that characterizes in compositional question answering and visual reasoning about real-world images.

The Conceptual Captions 12M (CC-12M) dataset consists of 12 million diverse and high-quality images paired with descriptive captions and titles.

The dataset used in the paper "Scaling Laws of Synthetic Images for Model Training". The dataset is used for supervised image classification and zero-shot classification tasks.

The Amazon Berkeley Objects Dataset (ABO) is a public available e-commerce dataset with multiple images per product.

The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships.

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...

The COCO-QA dataset is used for visual question answering task. It consists of 123,287 images and 78,736 train and 38,948 test questions.

The Microsoft COCO dataset was used for training and evaluating the CNNs because it has become a standard benchmark for testing algorithms aimed at scene understanding and...

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...