Pornography detection using BossaNova video descriptor

  title={Pornography detection using BossaNova video descriptor},
  author={Carlos Caetano and Sandra Eliza Fontes de Avila and Silvio Jamil Ferzoli Guimar{\~a}es and Arnaldo de Albuquerque Ara{\'u}jo},
  journal={2014 22nd European Signal Processing Conference (EUSIPCO)},
In certain environments or for certain publics, porno-graphic content may be considered inappropriate, generating the need to be detected and filtered. Most works regarding pornography detection are based on the detection of human skin. However, a shortcoming of these kind of approaches is related to the high false positive rate in contexts like beach shots or sports. Considering the development of low-level local features and the emergence of mid-level representations, we introduce a new video… CONTINUE READING