Abstract: A system for training a neural-network-based floating-point-to-binary feature vector encoder preserves the locality relationships between samples in an input space over to an output space. The system includes a neural network under training and a probability distribution loss function generator. The neural network has floating-point inputs and floating-point pseudo-bipolar outputs. The generator compares an input probability distribution constructed from floating-point cosine similarities of an input space and an output probability distribution constructed from floating-point pseudo-bipolar pseudo-Hamming similarities of an output space. The system includes a proxy vector set generator to take a random sampling of vectors from training data for a proxy set, a sample vector selector to select sample vectors from the training data and a KNN vector set generator to find a set of k nearest neighbors closest to each sample vector from said proxy set for a reference set.

Abstract: A system for training a neural-network-based floating-point-to-binary feature vector encoder preserves the locality relationships between samples in an input space over to an output space. The system includes a neural network under training and a probability distribution loss function generator. The neural network has floating-point inputs and floating-point pseudo-bipolar outputs. The generator compares an input probability distribution constructed from floating-point cosine similarities of an input space and an output probability distribution constructed from floating-point pseudo-bipolar pseudo-Hamming similarities of an output space. The system includes a proxy vector set generator to take a random sampling of vectors from training data for a proxy set, a sample vector selector to select sample vectors from the training data and a KNN vector set generator to find a set of k nearest neighbors closest to each sample vector from said proxy set for a reference set.

Abstract: A system and method for estimating an expected waiting time for a person entering a queue may receive image data captured from at least one image capture device during a period of time prior to the person entering the queue; calculate, based on the image data, one or more prior waiting time estimations, a queue handling time estimation, and a queue occupancy; assign a module weight to each of the one or more prior waiting time estimations and to the queue handling time estimation; generate, based on at least the calculations of the one or more prior waiting time estimations, the queue handling time estimation, and the respective module weights, a recent average handling time for the prior period of time; and determine the expected waiting time based on the recent average handling time and the queue occupancy.