Xichun Sheng

scene text (2) continual learning (1) multi-task learning (1) temporal modeling (1) prototype learning (1) knowledge distillation (1) source-free domain adaptation (1) multimodal learning (1) audio-visual learning (1) incremental learning (1) video understanding (1) class-incremental learning (1) unsupervised domain adaptation (1) adversarial training (1) cross-modal retrieval (1) prompt learning (1) variational autoencoder (1) knowledge preservation (1) prompt tuning (1) text-video retrieval (1)