Kent Fujiwara

motion generation (3) motion-language model (3) 3d vision (2) point cloud analysis (2) neural network (2) global convergence (1) weakly supervised learning (1) transfer learning (1) multi-modal learning (1) weakly-supervised learning (1) embedding learning (1) temporal grounding (1) cross-modal retrieval (1) video-text alignment (1) human motion (1) cross-modal learning (1) instruction tuning (1) multiple instance learning (1) implicit representation (1) point cloud (1)