Weiying Xue

semantic segmentation (3) contact detection (2) depth estimation (2) scene understanding (1) depth perception (1) object detection (1) knowledge distillation (1) human-object interaction (1) human pose estimation (1) multi-task feature learning (1) loss function (1) human-object interaction detection (1) transformer encoder (1) spatial awareness (1) cross-modal transformer (1) query initialization (1) human-object contact (1) prompt guidance (1) texture restoration (1) human object interaction (1)