Quantum Data Reduction with Application to Video Classification

TL;DR

This paper presents a hybrid quantum-classical approach for video classification that reduces data size to mitigate quantum data loading challenges, demonstrating effective classification with a smaller dataset.

Contribution

It introduces a novel quantum data reduction technique for video classification, addressing the quantum data loading bottleneck with practical verification on sign videos.

Findings

Reduced dataset retains enough information for accurate classification

The method alleviates quantum data loading bottleneck

Successful quantum classification on sign videos

Abstract

We investigate a quantum video classification method using a hybrid algorithm. A quantum-classical step performs a data reduction on the video dataset and a quantum step -- which only has access to the reduced dataset -- classifies the video to one of k classes. We verify the method using sign videos and demonstrate that the reduced dataset contains enough information to successfully classify the data, using a quantum classification process. The proposed data reduction method showcases a way to alleviate the "data loading" problem of quantum computers for the problem of video classification. Data loading is a huge bottleneck, as there are no known efficient techniques to perform that task without sacrificing many of the benefits of quantum computing.