29 datasets found

The dataset used in this paper for image annotation, consisting of 4,999 annotated images with a vocabulary of up to 200 keywords.

A dataset of images annotated with semantic tuples, including predicates, actors, and locatives.

This dataset contains images paired with multiple human-annotated descriptions in the form of sentences.

Multi-class cell segmentation in high-resolution Giga-pixel whole slide images (WSI) is critical for various clinical applications. Training such an AI model typically requires...

A dataset for autonomous driving.

The dataset used in the experiment consists of 50 images equally distributed between five classes: aircraft, bird, bicycle, boat, and dog. Each class has 5 true positive images...

A vision-language pre-training dataset, BLIP2, which consists of 100 million image-text pairs.

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 multi-view clustering dataset, which contains 6 views of 2000 samples each. The dataset is used to evaluate the performance of the proposed...

Visual grounding is the task of localizing a language query in an image. The output is often a bounding box as drawn in the yellow color.

The Flickr30K Entities dataset consists of 31,783 images each matched with 5 captions. The dataset links distinct sentence entities to image bounding boxes, resulting in 70K...

The SBD dataset is a benchmark dataset for semantic segmentation and object detection.

The dataset used in the paper is the MSCOCO validation set.

A dataset of images with annotated objects.

The CornerNet dataset is a benchmark for bottom-up object detection. It contains 80 categories and over 1.5 million object instances.

A dataset of images with pothole annotations from various sources, including Google Earth Pro, AUTOPILOT videos, and GoPro camera images.

The RefCOCOg dataset is a reconstructed dataset of the MS-COCO dataset, containing 85,474 referring expressions for 54,822 objects in 26,711 images.

The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.

The COCO test-dev dataset is used for instance segmentation. It contains 20k test-dev images.

The COCO dataset is a large-scale dataset for object detection, semantic segmentation, and captioning. It contains 80 object categories and 1,000 image instances per category,...