Li Zhu

document grounding (2) representation learning (2) image captioning (2) benchmark evaluation (1) anomaly detection (1) feature extraction (1) domain adaptation (1) scene understanding (1) uncertainty quantification (1) prototype learning (1) visual question answering (1) natural language generation (1) text generation (1) code generation (1) emotion recognition (1) text classification (1) cross-modal learning (1) superpixel segmentation (1) human pose estimation (1) vision transformer (1)