59 datasets found

A dataset for evaluating the performance of image tampering detection methods.

A large-scale benchmark archive for remote sensing image classification and retrieval.

The dataset used in this paper is a collection of images from different classes, including Africa, Monuments, Animals, and People.

The proposed method uses two benchmark datasets with different kinds of images, MNIST and CIFAR-10.

The ICDAR 2019 Competition on Image Retrieval for Historical Handwritten Documents dataset consists of 20,000 document images representing about 10,000 writers, divided into...

Part of sift descriptors extracted from Oxford building used in image retrieval.

This dataset is used for fine-grained sketch-based image retrieval (FG-SBIR) and sketch style transfer. It contains 50,025 shoe photos.

The dataset used in this study is the ImageCLEF corpus.

The MIRFLICKR-25K dataset consists of 25015 images and 223635 tags, where each image is associated with several textual tags and annotated with a 24-dimensional semantic label.

Flickr8K dataset is a collection of 8,000 images with 5 sentences describing each image content

The CVUSA and CVACT datasets are used for cross-view geolocalization. The VIGOR dataset is used for cross-view image retrieval and 3-DoF pose estimation.

The CVUSA and CVACT datasets are used for cross-view geolocalization. The VIGOR dataset is used for cross-view image retrieval and 3-DoF pose estimation.

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search.

The paper introduces a plug-and-play descriptor that can be effectively adopted for image retrieval tasks without prior initialization or preparation.

The dataset used in the paper is a benchmark for image retrieval.

Self-supervised visual representation learning framework for ranking random image views.

The Holidays dataset is used for testing the performance of the HAE on visual feature translation.

MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval.

Fine-grained visual comparisons with local learning. This dataset comprises 50,025 shoe images. It consists of 4 attributes containing 34 classes each.

An open dataset for attribute classification and street-to-shop image retrieval, comprising 253,983 images and 9 attributes. Each attribute contains 185 classes.