Peng Sun

papers

877

total citations

papers (18)

Event-Based Fusion for Motion Deblurring with Cross-Modal Attention

ECCV 2022arXiv

191

citations

Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion

CVPR 2021arXiv

171

citations

Graph-Guided Architecture Search for Real-Time Semantic Segmentation

CVPR 2020arXiv

105

citations

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

CVPR 2024arXiv

citations

Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception

ICCV 2023arXiv

citations

Unlocking the Power of LSTM for Long Term Time Series Forecasting

AAAI 2025arXiv

citations

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

ICML 2024arXiv

citations

DSRC: Learning Density-Insensitive and Semantic-Aware Collaborative Representation Against Corruptions

AAAI 2025arXiv

citations

Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios

ICCV 2025arXiv

citations

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

ICML 2024

citations

Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection

ICCV 2025

citations

Towards Transferable Targeted Adversarial Examples

CVPR 2023

citations

ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments

CVPR 2024

citations

Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping

CVPR 2024

citations

Peng Sun

papers (18)

Event-Based Fusion for Motion Deblurring with Cross-Modal Attention

Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion

Graph-Guided Architecture Search for Real-Time Semantic Segmentation

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception

Unlocking the Power of LSTM for Long Term Time Series Forecasting

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Event-Based Frame Interpolation With Ad-Hoc Deblurring

Privacy-Preserving Adversarial Facial Features

A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

DSRC: Learning Density-Insensitive and Semantic-Aware Collaborative Representation Against Corruptions

Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection

Towards Transferable Targeted Adversarial Examples

ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments

Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping

papers (18)

Event-Based Fusion for Motion Deblurring with Cross-Modal Attention

Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion

Graph-Guided Architecture Search for Real-Time Semantic Segmentation

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception

Unlocking the Power of LSTM for Long Term Time Series Forecasting

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Event-Based Frame Interpolation With Ad-Hoc Deblurring

Privacy-Preserving Adversarial Facial Features

A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

DSRC: Learning Density-Insensitive and Semantic-Aware Collaborative Representation Against Corruptions

Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection

Towards Transferable Targeted Adversarial Examples

ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments

Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping