Classifying Video based on Automatic Content Detection Overview

TL;DR

This paper reviews state-of-the-art methods for multi-label video classification, focusing on developing a new approach to handle sequential frame data for automatic content detection.

Contribution

It provides an experimental analysis of current architectures and proposes a novel method for multi-label video classification based on automatic content detection.

Findings

Analyzed existing architectures for video classification.

Developed a new method for sequential data processing.

Enhanced multi-label classification accuracy.

Abstract

Video classification and analysis is always a popular and challenging field in computer vision. It is more than just simple image classification due to the correlation with respect to the semantic contents of subsequent frames brings difficulties for video analysis. In this literature review, we summarized some state-of-the-art methods for multi-label video classification. Our goal is first to experimentally research the current widely used architectures, and then to develop a method to deal with the sequential data of frames and perform multi-label classification based on automatic content detection of video.