Shentong Mo

Core AI (1)

audio-visual learning (5) contrastive learning (5) multimodal learning (3) self-supervised learning (3) representation learning (2) vision transformer (2) point cloud (2) generative model (2) masked modeling (2) diffusion model (2) image generation (2) 3d shape generation (2) multi-modal learning (2) weakly supervised learning (2) class-incremental learning (2) continual learning (2) point cloud generation (1) catastrophic forgetting (1) source separation (1) cross-modal learning (1)