43 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 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 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

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

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.

The Stanford Online Products (SOP) dataset contains 120,053 product images covering 22,634 categories. The training set is composed of 59,551 images of the first 11,318...

FS-COCO: A large-scale scene sketch dataset with fine-grained alignment among sketch, text, and photo.

SketchyCOCO: A large-scale scene sketch dataset with fine-grained alignment among sketch, text, and photo.

The dataset used in the paper for UAV-view geo-localization, which aims to match images of the same target from different platforms.

The dataset used in the paper for UAV-view geo-localization, which aims to match images of the same target from different platforms.

The dataset used for experiments on generic image retrieval, person re-identification, and low-shot semantic segmentation.

The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

The dataset used in the paper is a large-scale graph dataset, consisting of users and shows with multi-attribute edges. The graph is constructed by selecting user IDs and side...

Fine-grained sketch-based image retrieval (FG-SBIR) aims to minimize the distance between sketches and corresponding images in the embedding space.