Original paper

Learning from Ambiguously Labeled Face Images

Volume: 40, Issue: 7, Pages: 1653 - 1667
Published: Jul 1, 2018
Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the caption. We propose a Matrix Completion for Ambiguity Resolution (MCar) method for predicting the actual labels from ambiguously labeled images. This step is followed by learning a standard supervised classifier...
Paper Details
Learning from Ambiguously Labeled Face Images
Published Date
Jul 1, 2018
1653 - 1667
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.