It has been raising industrial and research interest to analyze the age biasing in various video formats. Here I'm proposing a project to make use of Redhen's enriched news audio and video dataset and analyze the age biasing in the news media. The primary work involved in this project is to develop a pipeline to create the audio and video inputs using Redhen's dataset, use existing external data source for ground truth, train Machine Learning(ML) models to detect the age signals, apply necessary filtering based on testing/evaluation metrics and combine the produced annotation with original inputs (encoding and merging the annotations).

Organization

Student

Xiaoyu Lu

Mentors

  • Karan Singla
  • Peter Uhrig
  • Javier Valenzuela
close

2020