Search Results for author:
Found 4 papers, 0 papers with code
Automatic Ground Truths: Projected Image Annotations for Omnidirectional Vision
We present a novel data set made up of omnidirectional video of multiple objects whose centroid positions are annotated automatically.
Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition
We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types.
A data set for evaluating the performance of multi-class multi-object video tracking
The ground truth data sets presented in this paper contain unique object IDs across 5 different classes of object (Car, Bus, Truck, Person, Cyclist) for 24 videos of 871 image frames each.
Understanding data augmentation for classification: when to warp?
In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
