Chenyang Ma

zero-shot learning (1) semantic segmentation (1) scene understanding (1) self-supervised learning (1) multimodal learning (1) 3d vision (1) egocentric vision (1) remote sensing (1) latent space (1) vision-language model (1) spatial reasoning (1) egocentric video (1) 3d understanding (1) zero-shot prompting (1) robotics task (1) trajectory planning (1) tactile sensing (1) intra-class variance (1) prototypical contrastive learning (1) self-supervised feature learning (1)