Easy Navigation through Instructional Videos using Automatically Generated Table of Content

The amount of instructional videos available online, already in tens of thousands of hours, is growing steadily. A major bottleneck in their wide spread usage is the lack of tools for easy consumption of these videos. In this demonstration, we present MMToC: Multimodal Method for Table of Content, a technique that automatically generates a table of content for a given instructional video and enables text-book-like efficient navigation through the video. MMToC quantifies word saliency for visual words extracted from the slides and spoken words obtained from the lecture transcript. These saliency scores are combined using a dynamic programming based segmentation algorithm to identify likely points in the video where the topic has changed. MMToC is a web-based modular solution that can be used as a stand alone video navigation solution or can be integrated with any e-platform for multimedia content management. MMToC can be seen in action on a sample video at http://104.130.241.45:8080/TopicTransitionV2/index.html.