Faceted navigation for browsing large video collection

Abstract

This paper presents a content-based interactive video browsing system, developed for the Video Browser Showdown 2016, with the aim of supporting a user to find specific video clips from a large video collection under time constraints. Since the target of this evaluation forum is to evaluate and demonstrate the development of interactive video search tools, we focus on known-item search tasks, rather than query-by-example or query-by-text approaches for large-scale image/video retrieval. In this paper, we describe an interactive video retrieval system which employs the concept filters and faceted navigation to aid users quickly and intuitively locate the interested content when browsing in a large video collections based on automatically extracted semantic concepts, object labels and attributes from video content.