265 datasets found

Roadway damage data collection using Google Street View and YOLOv7 for automatic road damage detection and classification.

Objectron dataset contains 9 categories of objects with 15k video clips and over 4M frames annotated with 3D object bounding boxes, camera poses, sparse point clouds, and...

The dataset used in the paper is ScanNetV2, a real-world dataset for indoor scenes. It contains 1205 training scenes and 312 testing scenes, with instance-level object bounding...

Open-Set Semi-Supervised Object Detection aims to leverage the unconstrained unlabeled images to improve an object detector trained with the available labeled data.

Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search task as a dual denoising process from noisy boxes and ReID embeddings to ground...

The Modanet dataset is a large-scale street fashion dataset with polygon annotations.

The dataset used in the paper is the Cars Overhead With Context (COWC) dataset, which contains images of cars in overhead imagery.

A dataset of images with annotated objects.

The Open Images dataset is a large-scale image dataset with a wide range of images, including but not limited to, street scenes, indoor scenes, and outdoor scenes.

The BDD100k dataset is a large-scale driving dataset containing 100,000 images of various weather conditions, including clear, rainy, foggy, and night-time.

The Market-1501 dataset is a large benchmark for person re-identification. It contains 12,000 images with 1,500 images per person, annotated with bounding boxes and masks for...

The ESD dataset offers finetuned weights for the 'car' and 'French-horn' classes.

The French-horn dataset comprises merely 10 identical prompts with different evaluation seeds.

The dataset used in the paper is the Pascal VOC 2012 dataset, which is a benchmark for instance segmentation. The dataset consists of 1464 images with 20 class categories and...

The dataset used for object detection on streaming video from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2015.

Detectron is a library for object detection.

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image...

The Hazy-COCO dataset is a synthetic dataset generated by adding haze to the MS COCO dataset.

The proposed YOLO-Former method seamlessly integrates the ideas of transformer and YOLOv4 to create a highly accurate and efficient object detection system.

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics.