Yuan Gong

multimodal learning (3) audio classification (2) spectrogram transformer (2) whisper model (2) latent space (2) contrastive learning (2) convolutional neural network (2) audio spectrogram transformer (2) self-supervised learning (2) attention mechanism (2) transfer learning (1) knowledge distillation (1) question answering (1) face animation (1) uncertainty modeling (1) 3d reconstruction (1) neural rendering (1) vision transformer (1) automatic speech recognition (1) person re-identification (1)