Video Logo Retrieval based on local Features

TL;DR

This paper introduces Video Logo Retrieval (VLR), an algorithm that uses local image features for accurate logo detection in videos, outperforming global feature-based methods without requiring training.

Contribution

The paper presents a novel local feature-based video logo retrieval algorithm that is flexible, training-free, and achieves higher accuracy than existing methods.

Findings

VLR outperforms state-of-the-art logo retrieval algorithms.

VLR achieves higher accuracy on SoccerNet and Stanford I2V benchmarks.

VLR does not require training after hyper-parameter setup.

Abstract

Estimation of the frequency and duration of logos in videos is important and challenging in the advertisement industry as a way of estimating the impact of ad purchases. Since logos occupy only a small area in the videos, the popular methods of image retrieval could fail. This paper develops an algorithm called Video Logo Retrieval (VLR), which is an image-to-video retrieval algorithm based on the spatial distribution of local image descriptors that measure the distance between the query image (the logo) and a collection of video images. VLR uses local features to overcome the weakness of global feature-based models such as convolutional neural networks (CNN). Meanwhile, VLR is flexible and does not require training after setting some hyper-parameters. The performance of VLR is evaluated on two challenging open benchmark tasks (SoccerNet and Standford I2V), and compared with other state-of-the-art logo retrieval or detection algorithms. Overall, VLR shows significantly higher accuracy compared with the existing methods.