Ting Lei

vision language model (2) human-object interaction detection (2) open-vocabulary detection (2) action recognition (1) object detection (1) egocentric vision (1) semi-supervised clustering (1) knowledge transfer (1) weakly supervised learning (1) temporal reasoning (1) question answering (1) multimodal learning (1) scene graph generation (1) video understanding (1) human-object interaction (1) visual question answering (1) semantic space (1) temporal modeling (1) prompt generation (1) few-shot learning (1)