Sicong Leng

video understanding (2) large vision-language model (2) causal inference (2) multimodal learning (2) visual grounding (2) object hallucination (2) anomaly detection (1) domain adaptation (1) contrastive learning (1) attention mechanism (1) medical imaging (1) multi-modal learning (1) transfer learning (1) visual reasoning (1) video anomaly detection (1) visual question answering (1) text-to-image generation (1) scene graph (1) message passing (1) curriculum learning (1)