265 datasets found

Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection.

AeroRIT is a large-scale aerial hyperspectral scene with pixel-wise annotations, composed of challenging factors like shadows, glint, and mixed pixels.

The unmanned aerial vehicle benchmark: Object detection and tracking.

A dataset for open-vocabulary object detection.

Deep convolutional neural networks (CNNs) have had a major impact in most areas of image understanding, including object category detection.

SSDD dataset contains 1160 images of resolution from 1m to 15m in total, where the training set includes 928 images and the test set includes the remaining 232 images.

DOTA dataset is a large-scale dataset for object detection in aerial images including 2806 aerial images with each image ranging from 800 × 800 to 4000 × 4000 pixels collected...

The VIPSeg dataset contains videos with annotations for video panoptic segmentation.

The COCO test-dev set is a subset of the COCO detection dataset.

The COCO validation set is a subset of the COCO detection dataset.

The COCO detection dataset is a large-scale object detection benchmark.

The YOLOv3 dataset is a dataset for object detection and classification.

The proposed framework generates a training dataset in heterogeneous cluttered backgrounds for object detection and classification.

Aerial imaging of ground targets is highly challenging because of various factors that affect light propagation through different mediums. Several convolutional neural...

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the OpenImages dataset to train their models.

KITTI 2012 is a real-world dataset in the outdoor scenario, and contains 194 training and 195 testing stereo image pairs with the size of 376 × 1240.

The CARLA dataset is a complex urban-like environment with multi-agent dynamics, pedestrians, intersections, cross-traffic, roundabout, and changing weather conditions.

A large-scale dataset for object detection in aerial images, containing 4,000 bridges in 1,576 images.

A large-scale dataset for object detection in aerial images, containing 2,541 bridges in 288 images.

Sketch-based object localization in natural images, where given a crude hand-drawn sketch of an object, the goal is to localize all the instances of the same object on the...