Abstract:
Detecting near-duplicate videos in the cloud is computationally intensive due to sheer number of videos and their large file sizes. To address this challenge, we propose ...Show MoreMetadata
Abstract:
Detecting near-duplicate videos in the cloud is computationally intensive due to sheer number of videos and their large file sizes. To address this challenge, we propose to improve algorithm efficiency by enhancing and revising existing metadata and content comparison methods, and to enable public access by developing a web service. As a proof of concept, a duplicate video detection system called ViDupe is developed that can quickly scans user’s Google drive for duplicates.
Date of Conference: 08-12 April 2019
Date Added to IEEE Xplore: 20 May 2019
ISBN Information:
Print on Demand(PoD) ISSN: 1573-0077
Conference Location: Arlington, VA, USA