Bag of Genres for Video Retrieval

TL;DR

The paper introduces the Bag of Genres, a compact video representation based on genre classification, improving video retrieval by capturing multiple concepts within videos more effectively.

Contribution

It proposes a novel Bag of Genres representation using a genre classifier-based visual dictionary, enhancing video retrieval with a more compact and effective feature.

Findings

Achieves comparable or superior results to state-of-the-art methods.

Provides a more compact representation than existing features.

Effective for both video genre and event retrieval.

Abstract

Often, videos are composed of multiple concepts or even genres. For instance, news videos may contain sports, action, nature, etc. Therefore, encoding the distribution of such concepts/genres in a compact and effective representation is a challenging task. In this sense, we propose the Bag of Genres representation, which is based on a visual dictionary defined by a genre classifier. Each visual word corresponds to a region in the classification space. The Bag of Genres video vector contains a summary of the activations of each genre in the video content. We evaluate the proposed method for video genre retrieval using the dataset of MediaEval Tagging Task of 2012 and for video event retrieval using the EVVE dataset. Results show that the proposed method achieves results comparable or superior to state-of-the-art methods, with the advantage of providing a much more compact representation than existing features.