Xiaodong Xie

7

Papers

25

Total Citations

Papers (7)

FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection

Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression

Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation

Multi-Agent Automated Machine Learning

Correlating Edge, Pose With Parsing

Training Spiking Neural Networks with Event-driven Backpropagation

Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks