Unsupervised Audio-Visual Lecture Segmentation

TL;DR

This paper introduces AVLectures, a large-scale educational dataset, and proposes an unsupervised method for segmenting lecture videos into topics using multimodal cues, improving navigation and engagement.

Contribution

The paper presents a new dataset for educational videos and a novel unsupervised segmentation method leveraging visual, textual, and OCR data.

Findings

Outperforms baseline methods on 15 courses

Effective multimodal feature matching for segmentation

Key factors identified through ablation studies

Abstract

Over the last decade, online lecture videos have become increasingly popular and have experienced a meteoric rise during the pandemic. However, video-language research has primarily focused on instructional videos or movies, and tools to help students navigate the growing online lectures are lacking. Our first contribution is to facilitate research in the educational domain, by introducing AVLectures, a large-scale dataset consisting of 86 courses with over 2,350 lectures covering various STEM subjects. Each course contains video lectures, transcripts, OCR outputs for lecture frames, and optionally lecture notes, slides, assignments, and related educational content that can inspire a variety of tasks. Our second contribution is introducing video lecture segmentation that splits lectures into bite-sized topics that show promise in improving learner engagement. We formulate lecture segmentation as an unsupervised task that leverages visual, textual, and OCR cues from the lecture, while clip representations are fine-tuned on a pretext self-supervised task of matching the narration with the temporally aligned visual content. We use these representations to generate segments using a temporally consistent 1-nearest neighbor algorithm, TW-FINCH. We evaluate our method on 15 courses and compare it against various visual and textual baselines, outperforming all of them. Our comprehensive ablation studies also identify the key factors driving the success of our approach.