Dezhong Peng

Interactive Cross-modal Learning for Text-3D Scene Retrieval

Deep Fuzzy Multi-view Learning for Reliable Classification

Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding

LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification

Neighbor-aware Contrastive Disambiguation for Cross-Modal Hashing with Redundant Annotations

Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification

SHE: Streaming-media Hashing Retrieval

CoPINN: Cognitive Physics-Informed Neural Networks

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL