彭铎｜同济大学｜学者主页

2026

Training-free Motion Factorization for Compositional Video Generation

Zi-Xuan Wang, Ziqin Zhou, Feng Chen, Duo Peng, Yi-Xin Hu, Changsheng Li, Yin-Jie Lei

arXiv.org

DOI

2026

Structure-Aware Diffusion Image Outpainting for Echocardiographic Field-of-View Extension

Ruijia He, Yi-Xin Hu, Jinze Liu, Qixin Zhang, Duo Peng, Yanyan Chen

Computers, Materials & Continua

DOI

2026

Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning

Zi-Xuan Wang, Yi-Xin Hu, Wen Li, Feng Chen, Yan Liu, Duo Peng, Yin-Jie Lei

2026

Driver Interaction Intent Prediction With Dynamic Scene Semantic Fusion for Intelligent Cockpit

Hong-Yu Hu, Xin Qiao, Zhiwen Wei, Duo Peng, Changjia Tian, Rui Zhao, Fei Gao

IEEE Transactions on Industrial Informatics

DOI

2026

VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding

Haiyue Zhang, Yi Bin, Xun Jiang, Zeyu Ma, Duo Peng, Guo-Qing Wang, Yang Yang, Heng Shen

arXiv.org

DOI

2025

Unified Prompt Attack Against Text-to-Image Generation Models

Duo Peng, Qiu-Hong Ke, Mark He Huang, Ping Hu, Jun Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2025

Test-Time Training with Adaptive Memory for Traffic Accident Severity Prediction

Duo Peng, Wei-Qi Yan

De Computis

DOI

2024

Harnessing Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation

Duo Peng, Zheng-Bo Zhang, Ping Hu, Qiu-Hong Ke, David K. Y. Yau, Jun Liu

European Conference on Computer Vision

DOI

2024

Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers

Zheng-Bo Zhang, Li Xu, Duo Peng, Hossein Rahmani, Jun Liu

European Conference on Computer Vision

DOI

2023

Unsupervised Domain Adaptation via Domain-Adaptive Diffusion

Duo Peng, Qiu-Hong Ke, ArulMurugan Ambikapathi, Yasin Yazici, Yin-Jie Lei, J. Liu

IEEE Transactions on Image Processing

DOI

2023

Deep Hypersphere Feature Regularization for Weakly Supervised RGB-D Salient Object Detection

Zhiyuan Liu, Munawar Hayat, Hong Yang, Duo Peng, Yinjie Lei

IEEE Transactions on Image Processing

DOI

2023

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition

Duo Peng, Li Xu, Qiu-Hong Ke, Ping Hu, Jun Liu

Neural Information Processing Systems

DOI

2023

Dear-Net: Learning Diversities for Skeleton-Based Early Action Recognition

Rui Wang, Jun Liu, Qiu-Hong Ke, Duo Peng, Yin-Jie Lei

IEEE transactions on multimedia

DOI

2023

Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation

Duo Peng, Ping Hu, Qiu-Hong Ke, J. Liu

IEEE International Conference on Computer Vision

DOI

2022

基于域不变特征表示学习的跨域语义分割研究

彭铎

《四川大学》

2022

Semantic-Aware Domain Generalized Segmentation

Duo Peng, Yin-Jie Lei, Munawar Hayat, Yulan Guo, Wen Li

Computer Vision and Pattern Recognition

DOI

2021

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

Duo Peng, Yin-Jie Lei, Ling-Qiao Liu, Ping-Ping Zhang, Jun Liu

IEEE Transactions on Image Processing

DOI

2021

Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation

Duo Peng, Yin-Jie Lei, Wen Li, Ping-Ping Zhang, Yulan Guo

IEEE International Conference on Computer Vision

DOI

2020

Hierarchical Paired Channel Fusion Network for Street Scene Change Detection

Yin-Jie Lei, Duo Peng, Ping-Ping Zhang, Qiuhong Ke, Hai-Feng Li

IEEE Transactions on Image Processing

DOI

彭铎

精选作品

期刊论文

Training-free Motion Factorization for Compositional Video Generation

Structure-Aware Diffusion Image Outpainting for Echocardiographic Field-of-View Extension

Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning

Driver Interaction Intent Prediction With Dynamic Scene Semantic Fusion for Intelligent Cockpit

VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding

Unified Prompt Attack Against Text-to-Image Generation Models

Test-Time Training with Adaptive Memory for Traffic Accident Severity Prediction

Harnessing Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation

Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers

Unsupervised Domain Adaptation via Domain-Adaptive Diffusion

Deep Hypersphere Feature Regularization for Weakly Supervised RGB-D Salient Object Detection

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition

Dear-Net: Learning Diversities for Skeleton-Based Early Action Recognition

Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation

基于域不变特征表示学习的跨域语义分割研究

Semantic-Aware Domain Generalized Segmentation

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation

Hierarchical Paired Channel Fusion Network for Street Scene Change Detection

研究方向