Yiwei Ma

semantic segmentation (4) referring expression (4) 3d referring expression segmentation (3) 3d vision (2) visual grounding (2) multimodal learning (2) human perception (1) scene understanding (1) benchmark evaluation (1) model evaluation (1) feature matching (1) point cloud (1) cross-modal learning (1) image generation (1) image translation (1) multilingual translation (1) multi-modal learning (1) machine translation (1) instance segmentation (1) few-shot learning (1)