Liang-Yan Gui

human-object interaction (4) diffusion model (3) 3d scene understanding (2) visual grounding (2) motion capture (2) 3d reconstruction (2) object detection (2) motion generation (2) 3d generation (2) vision-language model (2) domain adaptation (1) multimodal learning (1) autonomous driving (1) 3d vision (1) question answering (1) imitation learning (1) contrastive learning (1) data augmentation (1) knowledge distillation (1) semantic segmentation (1)