Login / Signup

Weakly Supervised Representation Learning for Audio-Visual Scene Analysis.

Sanjeel ParekhSlim EssidAlexey OzerovNgoc Q. K. DuongPatrick PérezGaël Richard
Published in: IEEE ACM Trans. Audio Speech Lang. Process. (2020)
Keyphrases
  • weakly supervised
  • scene analysis
  • audio visual
  • multi modal
  • object class
  • relation extraction
  • data sets
  • topic models
  • natural language
  • probabilistic model
  • image representation