DALL-E; Zero-Shot Text-to-Image Generation
ICML 2021
Multimodal Transformer, Cross-modal attention, self-attention
Signal Data, Wav2Vec, SincNet, PASE
Signal Data, Wav2Vec, SincNet, PASE
Signal Data, Fourier Transform, MFCC
Signal Data, Fourier Transform, MFCC
Multimodal Learning, Multimodal Representations
Multimodal Learning, Translation
Multimodal Learning, Multimodal Representations
Multimodal Deep Learning에 대한 소개글