Dynamic Object Scanning: Object-Based Elastic Timeline for Quickly Browsing First-Person Videos

Seita Kayukawa, Keita Higuchi, Ryo Yonetani, Masanori Nakamura, Yoichi Sato, Shigeo Morishima

Abstract: This work presents the Dynamic Object Scanning (DO-Scanning), a novel interface that helps users browse long and untrimmed first-person videos quickly. The proposed interface offers users a small set of object cues generated automatically tailored to the context of a given video. Users choose which cue to highlight, and the interface in turn adaptively fast-forwards the video while keeping scenes with highlighted cues played at original speed. Our experimental results have revealed that the DO-Scanning has an efficient and compact set of cues arranged dynamically and this set of cues is useful for browsing a diverse set of first-person videos.