Yue Hu

Latest

• Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
• Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment
• MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering
• WLinker: Modeling Relational Triplet Extraction as Word Linking
• APER: AdaPtive Evidence-driven Reasoning Network for machine reading comprehension with unanswerable questions
• CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
• MCR-NET: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension
• Unsupervised Learning of Deterministic Dialogue Structure with Edge-Enhanced Graph Auto-Encoder
• Bi-directional Cognitive Thinking Network for Machine Reading Comprehension
• Learning cross-modal correlations by exploring inter-word semantics and stacked co-attention
• Learning Dual Encoding Model for Adaptive Visual Understanding in Visual Dialogue
• Cross-modal knowledge reasoning for knowledge-based visual question answering
• Cross-modal learning with prior visual relation knowledge
• Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
• DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue
• Coarse-to-Careful: Seeking Semantic-Related Knowledge for Open-Domain Commonsense Question Answering
• History-adaption knowledge incorporation mechanism for multi-turn dialogue system
• Prior Visual Relationship for Visual Question Answering
• Reasoning on the Relation: Enhancing Visual Representation for Visual Question Answering and Cross-modal Retrieval
• 2D-Convolution Based Feature Fusion for Cross-Modal Correlation Learning
• Fine-Grained Label Learning via Siamese Network for Cross-modal Information Retrieval
• Semantic Modeling of Textual Relationships in Cross-Modal Retrieval