Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder.

Chong Peng Liqiang He Dan Su

Published in: CoRR (2024)

Keyphrases

reinforcement learning
learning process
online learning
learning systems
motion estimation
learning problems
inductive inference
data sets
video sequences
active learning
multi modal
human computer interaction
background knowledge
learning scenarios
learning analytics