Large-Scale Video Search with Efficient Temporal Voting Structure

TL;DR

This paper introduces a fast, scalable video search system that combines robust content representation with efficient hashing and a novel voting scheme, enabling quick queries on large databases with limited resources.

Contribution

The work presents a new large-scale video search method using edge energy features, hashing, and a queue-based voting scheme for efficient, low-memory querying.

Findings

Fast query response on large video datasets

High recall rate achieved in searches

Low memory and disk usage during querying

Abstract

In this work, we propose a fast content-based video querying system for large-scale video search. The proposed system is distinguished from similar works with two major contributions. First contribution is superiority of joint usage of repeated content representation and efficient hashing mechanisms. Repeated content representation is utilized with a simple yet robust feature, which is based on edge energy of frames. Each of the representation is converted into hash code with Hamming Embedding method for further queries. Second contribution is novel queue-based voting scheme that leads to modest memory requirements with gradual memory allocation capability, contrary to complete brute-force temporal voting schemes. This aspect enables us to make queries on large video databases conveniently, even on commodity computers with limited memory capacity. Our results show that the system can respond to video queries on a large video database with fast query times, high recall rate and very low memory and disk requirements.