A Deep Siamese Network for Scene Detection in Broadcast Videos

TL;DR

This paper introduces a deep Siamese network that automatically segments broadcast videos into scenes by learning shot similarities, validated through experiments and a new benchmark dataset.

Contribution

The paper presents a novel deep Siamese network for scene detection, along with an improved evaluation metric and a new benchmark dataset for the task.

Findings

Effective scene segmentation demonstrated against recent methods.

Proposed performance measure aligns better with expected results.

New benchmark dataset facilitates future research.

Abstract

We present a model that automatically divides broadcast videos into coherent scenes by learning a distance measure between shots. Experiments are performed to demonstrate the effectiveness of our approach by comparing our algorithm against recent proposals for automatic scene segmentation. We also propose an improved performance measure that aims to reduce the gap between numerical evaluation and expected results, and propose and release a new benchmark dataset.