Liulei Li

video understanding (3) semantic segmentation (3) self-supervised learning (3) object detection (3) zero-shot learning (2) human-object interaction detection (2) contrastive learning (2) correspondence learning (2) video object segmentation (2) scene graph generation (1) multi-label classification (1) hierarchical classification (1) multimodal learning (1) text-to-image generation (1) person detection (1) temporal reasoning (1) first-order logic (1) dense correspondence (1) modality alignment (1) medical image segmentation (1)