HiVideo: Hierarchical Browsing Interface for Educational Videos

Abstract

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). SIGGRAPH ’22 Posters, August 07-11, 2022, Vancouver, BC, Canada © 2022 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-9361-4/22/08. https://doi.org/10.1145/3532719.3543226 users’ browsing habits. For example, if a user wants to find a certain approach at an academic conference, they will most likely obtain multiple results with video thumbnail and title after long-time searching. These interfaces may not allow users to intuitively know the video contents. We propose a video browsing interface, HiVideo, for academic presentations and educational videos, as shown in Fig. 1. When users retrieve the specified contents, the poster layer can help them explore the general video content rather than watching the whole video. To extract slides from a video, the proposed system leverages a frame detection approach, and a deep learning based document layout analysis approach [Shen et al. 2021] to extract visual information from the slides. In the user study, we verify that this proposed HiVideo interface can accommodate a wide range of usage scenarios for different users. In contrast to a previous video browsing interface [Weng et al. 2022], we adopt responsive web design so that users can achieve the better user experience even with mobile browsers.