252 datasets found

PASCAL 2007 dataset

The proposed approach is demonstrated on multiple vision tasks and modalities through a variety of applications.

Ocean eddies detection using YOLO models on SAR images

The dataset used in the paper is not explicitly described, but it is mentioned that it is a robotic task dataset.

Object detection using center points

The PASCAL VOC2012 dataset is a benchmark for object detection, containing 1464 images with corresponding labeled object instances for 20 classes.

The proposed approach is validated using various state-of-the-art network architectures (VGG and ResNet) on several well-known object detection benchmarks (i.e., PASCAL VOC 2007...

The MED-MNIST dataset is a simulated object detection dataset, created by copying and pasting digits from MNIST into a black background.

The OSDD dataset is a dataset tailored for state detection.

A high-quality dataset containing 348 different car models with physical dimensions and part-level annotations based on global and local deformations.

The COCO2017 dataset is utilized to evaluate the quantization performance for object detection task.

OAK dataset for egocentric video understanding

EgoObjects dataset for object-centric scene understanding

The dataset used for the object detection challenge in DAC-SDC 2019.

The dataset used for the low power object detection challenge in DAC-SDC 2019.

The dataset used in the paper is COCO and D2-City, which are commonly used detection datasets.

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, models are unable to leverage...

The dataset used for this problem is presented in Honeybee Segmentation and Tracking Datasets project [Bozek et al., 2017]. One of the contributions of this work is an...

Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object...

The dataset used for the proposed MoCo-SAS framework, which consists of high-resolution Synthetic Aperture Sonar (SAS) data.