Zixu Wang

frame sampling (2) cross-modal correspondence (2) data augmentation (2) contrastive learning (2) machine translation (1) domain generalization (1) neural network training (1) visual question answering (1) zero-shot learning (1) knowledge distillation (1) model calibration (1) depth estimation (1) text generation (1) multimodal learning (1) image captioning (1) text classification (1) sensor fusion (1) synthetic data generation (1) audio classification (1) reinforcement learning (1)