A Simple and Effective Technique for Face Clustering in TV Series

Abstract

In this paper, we present a simple aggregation of framelevel CNN features in a face track to produce a tracklevel feature representation for face clustering in movies or videos. The approach is invariant of the image sequence and the number of frames the track has. We demonstrate the effectiveness of this strategy on three challenging benchmark video face… (More)

6 Figures and Tables

Topics

  • Presentations referencing similar topics