M3R: Masked Token Mixup and Cross-Modal Reconstruction for Zero-Shot Learning.

Peng Zhao Qiangchang Wang Yilong Yin

Published in: ACM Multimedia (2023)

Keyphrases

cross modal
multi modal
multimedia databases
multimedia retrieval
visual data
image retrieval
image search
visual recognition
visual similarity
perceptual information
multimedia
image sequences
nearest neighbor