Picture for Huadong Ma

Huadong Ma

Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation

Add code
Jul 19, 2024
Viaarxiv icon

Frequency-based Matcher for Long-tailed Semantic Segmentation

Add code
Jun 06, 2024
Viaarxiv icon

G3R: Generating Rich and Fine-grained mmWave Radar Data from 2D Videos for Generalized Gesture Recognition

Add code
Apr 23, 2024
Viaarxiv icon

NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results

Add code
Apr 17, 2024
Figure 1 for NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
Figure 2 for NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
Figure 3 for NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
Figure 4 for NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
Viaarxiv icon

Learning Exposure Correction in Dynamic Scenes

Add code
Mar 10, 2024
Viaarxiv icon

Region-Aware Exposure Consistency Network for Mixed Exposure Correction

Add code
Feb 28, 2024
Viaarxiv icon

Mutual Distillation Learning For Person Re-Identification

Add code
Jan 12, 2024
Viaarxiv icon

Uncovering the human motion pattern: Pattern Memory-based Diffusion Model for Trajectory Prediction

Add code
Jan 08, 2024
Viaarxiv icon

Multi-Stage Contrastive Regression for Action Quality Assessment

Add code
Jan 05, 2024
Figure 1 for Multi-Stage Contrastive Regression for Action Quality Assessment
Figure 2 for Multi-Stage Contrastive Regression for Action Quality Assessment
Figure 3 for Multi-Stage Contrastive Regression for Action Quality Assessment
Figure 4 for Multi-Stage Contrastive Regression for Action Quality Assessment
Viaarxiv icon

Efficient Cloud-edge Collaborative Inference for Object Re-identification

Add code
Jan 04, 2024
Viaarxiv icon