Login / Signup

Leveraging Pre-trained BERT for Audio Captioning.

Xubo LiuXinhao MeiQiushi HuangJianyuan SunJinzheng ZhaoHaohe LiuMark D. PlumbleyVolkan KiliçWenwu Wang
Published in: CoRR (2022)
Keyphrases
  • pre trained
  • training data
  • multimedia
  • training examples
  • visual information
  • signal processing
  • audio visual
  • decision trees
  • viewpoint
  • real time
  • small number
  • text classification
  • visual data
  • control signals