MultimodalAffectiveComputing / FV2ES

A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition
30 stars 3 forks source link

the differences between The Hierarchical-Attention Spectrum Computing Module and Pyramid Vision Transformer #6

Closed CHEN-WDan closed 1 year ago

CHEN-WDan commented 1 year ago

Hello, I have some confusion, may I ask what is the difference between the Hierarchical-Attention Spectrum Computing Module and Pyramid Vision Transformer? I found the principle of the two to be similar. Thank you.

CHEN-WDan commented 1 year ago

Hello, the question has solved. Sorry to bother you. Sincerely.