Furthermore, the experimental results on the different dataset will be discussed in this section.
Research questions and access to the whole dataset will be discussed within the TRI database scientific committee and has to be approved by it.
The virtual camera was set in a similar configuration to the camera in our real-world dataset which will be discussed in Section 4, with zero roll and heading and −20° pitch.
As LOOCV does not depend on the order of patients in the dataset, these results will be discussed in details.
All parameter model tuning and testing, e.g., using cross-validation, were done using only the training dataset L. Evaluation, as will be discussed in this section, was done using documents in the dataset Q. Documents in Q were never used for training and parameter tuning.
This observation is based on the analysis of a single dataset and cannot be generalized, as will be discussed in this work.
Multiple issues related to building crowd datasets, such as annotation and increasing scene diversity, will be discussed.
