Login / Signup

More than Vanilla Fusion: a Simple, Decoupling-free, Attention Module for Multimodal Fusion Based on Signal Theory.

Peiwen SunYifan ZhangZishan LiuDonghao ChenHonggang Zhang
Published in: CoRR (2023)
Keyphrases
  • multimodal fusion
  • relevance feedback
  • high robustness
  • multimodal interfaces
  • information retrieval
  • audio visual
  • data mining
  • computer vision
  • three dimensional
  • face recognition
  • human computer interaction