Xiaojiang Peng

papers

1,412

total citations

papers (12)

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

CVPR 2020arXiv

587

citations

Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition

ECCV 2020arXiv

237

citations

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

CVPR 2025arXiv

citations

DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment

ECCV 2024

citations

Dataset Growth

ECCV 2024arXiv

citations

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

ICCV 2025arXiv

citations

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

AAAI 2025

citations

Xiaojiang Peng

papers (12)

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition

Visual Compositional Learning for Human-Object Interaction Detection

Affordance Transfer Learning for Human-Object Interaction Detection

Detecting Human-Object Interaction via Fabricated Compositional Learning

Suppressing Mislabeled Data via Grouping and Self-Attention

An Efficient Training Approach for Very Large Scale Face Recognition

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment

Dataset Growth

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

papers (12)

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition

Visual Compositional Learning for Human-Object Interaction Detection

Affordance Transfer Learning for Human-Object Interaction Detection

Detecting Human-Object Interaction via Fabricated Compositional Learning

Suppressing Mislabeled Data via Grouping and Self-Attention

An Efficient Training Approach for Very Large Scale Face Recognition

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment

Dataset Growth

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval