Xuming He

Latest

• Grounded Image Text Matching with Mismatched Relation Reasoning
• Calip: Zero-shot enhancement of clip with parameter-free attention
• HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
• Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition(*Best Student Paper*)
• ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning
• KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation
• General Incremental Learning with Domain-aware Categorical Representations
• SGTR: End-to-end Scene Graph Generation with Transformer
• Dynamic Grained Encoder for Vision Transformers
• Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
• Contour Completion without Region Segmentation
• Building Scene Models by Completing and Hallucinating Depth and Semantics
• Learning Dynamic Hierarchical Models for Anytime Scene Labeling
• Learning to Co-Generate Object Proposals with a Deep Structured Network
• Learning to Generate Object Segment Proposals with Multi-modal Cue
• Semantic Context and Depth-aware Object Proposal Generation
• SentiCap: Generating Image Descriptions with Sentiments