Login / Signup

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation.

Yusong WuKe ChenTianyu ZhangYuchen HuiTaylor Berg-KirkpatrickShlomo Dubnov
Published in: CoRR (2022)
Keyphrases
  • feature fusion
  • multiple features
  • feature extraction
  • keywords
  • fusion algorithm
  • visual information
  • multi sensor
  • multiscale
  • feature selection
  • high dimensional
  • visual features
  • semantic information
  • low level features