Comparative Analysis of Image, Video, and Audio Classifiers for Automated News Video Segmentation
This work addresses the challenge of organizing and retrieving unstructured news video content for media applications like archiving and search, but it is incremental as it focuses on comparative analysis of existing methods.
This paper tackled the problem of automated news video segmentation by comparing image, video, and audio classifiers, finding that image-based classifiers like ResNet achieved 84.34% accuracy, outperforming more complex temporal models with fewer computational resources.
News videos require efficient content organisation and retrieval systems, but their unstructured nature poses significant challenges for automated processing. This paper presents a comprehensive comparative analysis of image, video, and audio classifiers for automated news video segmentation. This work presents the development and evaluation of multiple deep learning approaches, including ResNet, ViViT, AST, and multimodal architectures, to classify five distinct segment types: advertisements, stories, studio scenes, transitions, and visualisations. Using a custom-annotated dataset of 41 news videos comprising 1,832 scene clips, our experiments demonstrate that image-based classifiers achieve superior performance (84.34\% accuracy) compared to more complex temporal models. Notably, the ResNet architecture outperformed state-of-the-art video classifiers while requiring significantly fewer computational resources. Binary classification models achieved high accuracy for transitions (94.23\%) and advertisements (92.74\%). These findings advance the understanding of effective architectures for news video segmentation and provide practical insights for implementing automated content organisation systems in media applications. These include media archiving, personalised content delivery, and intelligent video search.