Login / Signup

Siamese Transformer for Saliency Prediction Based on Multi-Prior Enhancement and Cross-Modal Attention Collaboration.

Fazhan YangXingge GuoSong LiangPeipei ZhaoShanhua Li
Published in: IEICE Trans. Inf. Syst. (2023)
Keyphrases
  • cross modal
  • multi modal
  • visual attention
  • saliency map
  • visual recognition
  • multimedia retrieval
  • image retrieval
  • multimedia databases
  • perceptual information
  • eye movements
  • semantic concepts
  • high dimensional