74 datasets found

A dataset containing 33,698 pedestrian images with 221 pedestrian identities.

The LXMERT dataset is used for visual question answering task. It uses pre-trained weights provided by Tan and Bansal (2019) and fine-tunes it with adaptive approaches mentioned...

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...

The Objects365 dataset is a large-scale object detection dataset containing 365,000 images with 365 categories.

The dataset used in this study is a collection of ABR reports in PDF format, with 187 image samples (116 normal samples and 71 abnormal samples).

FER2013 is a crowdsourced dataset. Each image was individually labeled by 40 taggers for the sake of rigor.

SAR ship detection dataset (SSDD) is used for training and testing the proposed SAR ship detection method based on Swin Transformer and Feature Enhancement Feature Pyramid...

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 Salinas dataset was acquired over the Salinas Valley in California and gathered by the AVIRIS sensor.

Single Image Super-Resolution (SR) aims to generate a High Resolution (HR) image I SR from a low resolution (LR) im-age I LR such that it is similar to original HR image I HR....

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.

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...

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...