Yasutomo Kawanishi

action recognition (1) scene understanding (1) object detection (1) visual question answering (1) knowledge distillation (1) multimodal learning (1) cross-modal learning (1) 3d vision (1) multi-modal learning (1) human pose estimation (1) multimodal interaction (1) human-robot interaction (1) multi-view learning (1) real-time processing (1) human action recognition (1) object relationships (1) view consistency (1) transformer network (1) egocentric video (1) 3d gaussian (1)