Login / Signup

MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning.

Ruize XuRuoxuan FengShi-Xiong ZhangDi Hu
Published in: ICASSP (2023)
Keyphrases
  • multi modal
  • audio visual
  • fine grained
  • coarse grained
  • multi modality
  • databases
  • access control
  • image annotation
  • cross modal
  • search engine
  • high level
  • feature vectors
  • text classification
  • single modality