Learning to Recognize Faces from Videos and Weakly Related Information Cues

Martin Köstinger, Paul Wohlhart, Peter Roth, Horst Bischof

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


Videos are often associated with additional information that could be valuable for interpretation of their content. This especially applies for the recognition of faces within video streams, where often cues such as transcripts and subtitles are available. However, this data is not completely reliable and might be ambiguously labeled. To overcome these limitations, we take advantage of semi-supervised (SSL) and multiple instance learning (MIL) and propose a new semi-supervised multiple instance learning (SSMIL) algorithm. Thus, during training we can weaken the prerequisite of knowing the label for each instance and can integrate unlabeled data, given only probabilistic information in form of priors. The benefits of the approach are demonstrated for face recognition in videos on a publicly available benchmark dataset. In fact, we show exploring new information sources can considerably improve the classification results.
Original languageEnglish
Title of host publication2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2011
Pages23 - 28
ISBN (Electronic)978-145770845-9
Publication statusPublished - 2011
EventIEEE International Conference on Advanced Video and Signal Based Surveillance: AVSS 2011 - Klagenfurt, Austria
Duration: 30 Aug 20112 Sept 2011


ConferenceIEEE International Conference on Advanced Video and Signal Based Surveillance

Fields of Expertise

  • Information, Communication & Computing

Cite this