249 datasets found

The Car Accident Detection and Prediction (CADP) dataset is a novel dataset for accident forecasting using traffic camera views. It provides a novel view for traffic accident...

The SWiG dataset is a large-scale visual grounding dataset, where the task is to predict the object in an image.

The PASCAL VOC dataset contains 20 classes, including person, animal, vehicle, and indoor, with 9,963 images containing 24,640 annotated objects.

Camouflaged object detection (COD) aims to search and segment camouflaged objects from single image.

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage...

Remote sensing images have different shooting angles and methods compared to ordinary ones, which makes remote sensing images play an irreplaceable role in some areas.

The dataset used in the paper is a collection of adversarial patches, with each patch designed to evade object detection models.

A novel road rutting dataset containing 949 images from heterogeneous sources.

The Pascal VOC, Pascal Context, COCO-Object, Cityscapes, and ADE20k datasets are used for evaluation of the proposed method.

SA-1B is a large-scale benchmark for instance segmentation and object detection.

LVIS is a large-scale benchmark for instance segmentation and object detection.

The COCO dataset is a large-scale dataset for object detection and image classification.

The COCO 2014 validation set is used for evaluating the performance of the proposed method.

Linley et al. (2014) - Microsoft COCO

The COCO-stuff dataset is a large-scale dataset for scene understanding, object detection, and image synthesis.

The CAMO dataset is the first COD dataset, containing 1,250 camouflaged images and 1,250 non-camouflaged images.

A large-scale dataset for object detection in aerial images, containing 11,268 images and 1,793,658 objects.

Dataset for autonomous package delivery using micro-class UAVs, consisting of 5 videos at 30 frames per second and 1100 keyframes annotated with a bounding box enclosing the...

The VisDrone-2019-DET dataset is a comprehensive benchmark facilitating the integration of drone technology and visual perception.

A large scale event-based detection dataset for automotive.