Cyclic Autoencoder for Multimodal Data Alignment Using Custom Datasets

Zhenyu Tang, Jin Liu, Chao Yu, Y. Ken Wang

Abstract: The subtitle recognition under multimodal data fusion in this paper aims to recognize text lines from image and audio data. Most existing multimodal fusion methods tend to be associated with pre-fusion as well as post-fusion,... | Find, read and cite all the research you need on Tech Science Press