CroMM-VSR: Cross-Modal Memory Augmented Visual Speech Recognition.

Minsu Kim Joanna Hong Se Jin Park Yong Man Ro

Published in: IEEE Trans. Multim. (2022)

Keyphrases

cross modal
visual speech recognition
multi modal
hidden markov models
lip reading
image retrieval
visual recognition
multimedia retrieval
multimedia databases
information retrieval
dynamic textures
computer vision
co occurrence
multimedia data
image annotation