Fight Scene Detection for Movie Highlight Generation System

TL;DR

This paper introduces a BiLSTM-based fight scene detection model for movies that automates highlight generation, achieving higher accuracy than previous CNN-based methods, thereby streamlining the creation of engaging movie summaries.

Contribution

The paper presents a novel deep learning model using BiLSTM for automatic fight scene detection in movies, improving accuracy over existing CNN-based approaches.

Findings

Achieves 93.5% accuracy in fight scene detection

Outperforms 2D CNN with Hough Forests (92%)

Significantly better than 3D CNN (65%)

Abstract

In this paper of a research based project, using Bidirectional Long Short-Term Memory (BiLSTM) networks, we provide a novel Fight Scene Detection (FSD) model which can be used for Movie Highlight Generation Systems (MHGS) based on deep learning and Neural Networks . Movies usually have Fight Scenes to keep the audience amazed. For trailer generation, or any other application of Highlight generation, it is very tidious to first identify all such scenes manually and then compile them to generate a highlight serving the purpose. Our proposed FSD system utilises temporal characteristics of the movie scenes and thus is capable to automatically identify fight scenes. Thereby helping in the effective production of captivating movie highlights. We observe that the proposed solution features 93.5% accuracy and is higher than 2D CNN with Hough Forests which being 92% accurate and is significantly higher than 3D CNN which features an accuracy of 65%.