Wenfeng Song

diffusion model (3) human-object interaction (2) domain adaptation (1) weakly supervised learning (1) multimodal learning (1) egocentric vision (1) latent diffusion (1) disentangled representation (1) 3d scene understanding (1) object tracking (1) human motion synthesis (1) motion generation (1) multi-modal learning (1) convolutional neural network (1) attention mechanism (1) real-time rendering (1) 3d reconstruction (1) latent diffusion model (1) textual description (1) unsupervised learning (1)