Xun Jiang

So Far Yet So Near: Time Series Data Augmentation with Exploring non-Semantic Boundaries based on Reinforcement Learning

Heterogeneous Graph Embedding for Multimodal Multi-Label Emotion Recognition

Geometric Gradient Divergence Modulation for Imbalanced Multimodal Learning

Resisting Noise in Pseudo Labels: Audible Video Event Parsing With Evidential Learning

Cross-modal attention preservation with self-contrastive learning for composed query-based image retrieval