Finding Celebrities in Video

ABSTRACT We present a system for finding celebrities in videos that uses face information in conjunction with text or speech. We achieve an approximate tripling of precision for searches over the use of transcripts or speech alone. Our work is motivated by the recent growth of personal video record- ing devices such as TiVo, which makes watching television more like information retrieval. We use a large dataset con- sisting of 13.5 hours of commercial video, which presents a challenging speech and face recognition environment. Faces are extracted using a face detector and processed via ker-