361 datasets found

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 dataset for image classification, object detection, and visual relationship detection.

The dataset used in the paper is the MS-COCO 2017 detection dataset.

Region-based Fully Convolutional Networks for object detection

The ImageNet VID dataset is a large scale benchmark for video object detection task consisting of 3,862 videos in the training set and 555 videos in the validation set. 30...

The VisDrone2019 dataset contains 10,209 high-resolution images with ten categories: pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, and motor.

The dataset used in the paper is the VOC dataset, which is a dataset for object detection and segmentation.

The Foggy Cityscapes dataset is an extension to the Cityscapes dataset, containing 5k diverse real-world urban driving scenes with fog.

The OTB-2015 dataset is a benchmark for visual object tracking, containing 1000 videos with 1000 frames each.

The VOT-2018 dataset is a large-scale and challenging dataset for visual object tracking.

YOLOv4 dataset contains object detection tasks.

Object detection in 20 years: A survey dataset contains object detection tasks.

The proposed method of automatic dataset generation for cards detection and classification makes it possible to obtain any number of images of any size, which can be used to...

The Argoverse dataset includes 65 training and 24 validation sequences recorded in Miami and Pittsburgh.

The ACFR Apple dataset is used for object detection tasks.

The proposed system uses a sophisticated framework using computer vision techniques for object detection and automatic license plate recognition (ALPR) for reading and...

Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects.

Fast R-CNN is a clean and fast update to R-CNN and SPPnet. It uses a single-stage training algorithm that jointly learns to classify object proposals and refine their spatial...

CornerNet detects objects as a pair of keypoints— the top-left corner and bottom-right corner of the bounding box.

This dataset contains images of cats and dogs, which is used for training deep neural networks.