Jiuxiang Gu

Latest

• DocLayoutTTS: Dataset and Baselines for Layout-informed Document-level Neural Speech Synthesis
• DocTime: A Document-level Temporal Dependency Graph Parser
• Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns
• FedKC: Federated Knowledge Composition for Multilingual Natural Language Understanding
• Interactive Image Generation with Natural-Language Feedback
• Unsupervised Cross-lingual Image Captioning
• Unified Pretraining Framework for Document Understanding
• Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models
• Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection
• Multi-Scale Aligned Distillation for Low-Resolution Detection
• SelfDoc: Self-Supervised Document Representation Learning
• Self-Supervised Relationship Probing
• Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video Prediction
• Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning
• Resilient Load Restoration in Microgrids Considering Mobile Energy Storage Fleets: A Deep Reinforcement Learning Approach
• Bridging images and natural language with deep learning
• Unpaired Image Captioning via Scene Graph Alignments
• Scene Graph Generation with External Knowledge and Image Reconstruction
• Unpaired Image Captioning by Language Pivoting
• Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
• Stack-Captioning: Coarse-to-Fine Learning for Image Captioning
• An Empirical Study of Language CNN for Image Captioning
• Recent Advances in Convolutional Neural Networks