张鹏｜山东科技大学｜学者主页

2026

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models

Tian Xu, Zixuan Wang, Guangyuan Wang, Li Hu, Zhong-Yi Zhang, Peng Zhang, Bangyi Zhang, Song-Hai Zhang

International Conference on Computer Graphics and Interactive Techniques

2026

MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

Zhong-Yi Zhang, Guangyuan Wang, Liucheng Hu, Wenbo Zhou, Peng Zhang, Tianyi Wei, Wei-Ming Zhang, Bang Zhang, Neng-Hai Yu

arXiv.org

DOI

2026

Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction

Chaonan Ji, Jin-Wei Qi, Peng Zhang, Bang Zhang

arXiv.org

DOI

2026

WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction

Liucheng Hu, Guangyuan Wang, Peng Zhang, Bang Zhang

arXiv.org

DOI

2026

Wan-Animate-2: Pushing the Application Boundaries of Character Animation

Guangyuan Wang, Liucheng Hu, Dechao Meng, Zhong-Yi Zhang, Peng Zhang, Xindi Zhang, Mingyang Huang, Ruoshi Zhang, Ke Sun, Zhe Zhang, Xingjun Wang, Gang Cheng, Haisen Xu, Bang Zhang

2026

Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation

Mingyang Huang, Peng Zhang, Liucheng Hu, Guangyuan Wang, Ruoshi Zhang, Yi Lu, Gang Cheng, Bang Zhang

arXiv.org

DOI

2026

PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

Chaonan Ji, Jin-Wei Qi, Sheng Xu, Peng Zhang, Bangyi Zhang

arXiv.org

DOI

2026

A Lightweight Passive Depression Detection System Based on Interpretable Facial Feature Analysis

Liang Zhang, Peng Zhang, Tianhuan Huang, Jian Zhao, Wei Xiang, Xianye Ben

IEEE Internet of Things Journal

DOI

2026

PSO-HEAD: Pseudo-Supervision Guided Spatial Optimization for View-Consistent 3D Full-Head Reconstruction

Peng Zhang, Yiheng Zhang, Xiaolin Zhang, Chongxin Liang, Caifeng Shan, Haojie Li

ACM Transactions on Multimedia Computing Communications and Applications

DOI

2026

Cross-Domain Knowledge Transfer Learning With Macro-Expression Priors for Micro-Expression Recognition

Yingying Guo, Xianye Ben, Peng Zhang, Chen Gong, Wei Xiang, Xiaolin Wu

IEEE Transactions on Affective Computing

DOI

2026

Cross-scale gated embedding graph model for skeleton-based anomaly detection

Yutong He, Peng Zhang, Tianhuan Huang, Xianye Ben, Lei Chen

Multimedia Systems

DOI

2026

基于视觉长短期记忆网络和双重注意力机制的微表情识别

包永堂，刘福仪，张鹏

《山东科技大学学报(自然科学版)》

2025

Exploring Timeline Control for Facial Motion Generation

Yifeng Ma, Jin-Wei Qi, Chaonan Ji, Peng Zhang, Bang Zhang, Zhidong Deng, Liefeng Bo

Computer Vision and Pattern Recognition

DOI

2025

Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation

Steven Xiao, Xindi Zhang, Dechao Meng, Qi Wang, Peng Zhang, Bang Zhang

arXiv.org

DOI

2025

OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking

Zhong-Jian Wang, Peng Zhang, Jin-Wei Qi, Yuan Wang, Sheng Xu, Bang Zhang

Neural Information Processing Systems

DOI

2025

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

Liucheng Hu, Guangyuan Wang, Zhen Shen, Xin Gao, Dechao Meng, Li'an Zhuo, Peng Zhang, Bang Zhang, Liefeng Bo

IEEE International Conference on Computer Vision

DOI

2025

SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild

Xindi Zhang, Dechao Meng, Steven Xiao, Qi Wang, Peng Zhang, Bang Zhang

arXiv.org

DOI

2025

Co-speech Gesture Video Generation via Motion-Based Graph Retrieval

Ya-Fei Song, Peng Zhang, Bangyi Zhang

arXiv.org

DOI

2025

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

Jin-Wei Qi, Chaonan Ji, Sheng Xu, Peng Zhang, Bang Zhang, Liefeng Bo

arXiv.org

DOI

2025

MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation

Mingyang Huang, Peng Zhang, Bangyi Zhang

arXiv.org

DOI

2025

MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody Animation

Dechao Meng, Steven Xiao, Xindi Zhang, Guangyuan Wang, Peng Zhang, Qi Wang, Bang Zhang, Liefeng Bo

arXiv.org

DOI

2025

Controllable and Expressive One-Shot Video Head Swapping

Chaonan Ji, Jin-Wei Qi, Peng Zhang, Bang Zhang, Liefeng Bo

IEEE International Conference on Computer Vision

DOI

2025

ConsistencyTrack: A robust multi-object tracker with a generation strategy of consistency model

Lifan Jiang, Zhihui Wang, Siqi Yin, Guangxiao Ma, Peng Zhang, Boxi Wu

Pattern Recognition

DOI

2025

Implicit Feature Augmentation for Cloth-Changing Person Re-identification

Yongtang Bao, Hao Zheng, Caifeng Shan, Peng Zhang

Lecture notes in computer science

DOI

2024

Corruption-Invariant Person Re-Identification via Coarse-to-Fine Feature Alignment

Xinyu Zhang, Peng Zhang, Caifeng Shan

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2024

Efficient abnormal behavior detection with adaptive weight distribution

Yutong He, Yefeng Qin, Lei Chen, Peng Zhang, Xianye Ben

Neurocomputing

DOI

2024

Identity Semantic Correspondence for Cloth-Changing Person Re-Identification

Yongtang Bao, Hao Zheng, Xiaolin Zhang, Kun Zhan, Peng Zhang

DOI

2024

Boosting Micro-Expression Recognition via Self-Expression Reconstruction and Memory Contrastive Learning

Yongtang Bao, Chenxi Wu, Peng Zhang, Caifeng Shan, Yue Qi, Xianye Ben

IEEE Transactions on Affective Computing

DOI

2023

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Liucheng Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, Liefeng Bo

Computer Vision and Pattern Recognition

DOI

2023

MaTe3D: Mask-Guided Text-based 3D-Aware Portrait Editing

Kangneng Zhou, Daiheng Gao, Xuan Wang, Jie Zhang, Peng Zhang, Xusen Sun, Longhao Zhang, Shiqi Yang, Bang Zhang, Liefeng Bo, Ya-Xing Wang, Ming-Ming Cheng

International Journal of Computer Vision

DOI

2023

VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior

Xusen Sun, Longhao Zhang, Hao Zhu, Peng Zhang, Bang Zhang, Xinya Ji, Kangneng Zhou, Daiheng Gao, Liefeng Bo, Xun Cao

International Conference on 3D Vision

DOI

2023

DanceMeld: Unraveling Dance Phrases with Hierarchical Latent Codes for Music-to-Dance Synthesis

Xin Gao, Liucheng Hu, Peng Zhang, Bang Zhang, Liefeng Bo

arXiv.org

DOI

2023

Pedestrian Attribute Recognition via Spatio-temporal Relationship Learning for Visual Surveillance

Zhenyu Liu, Da Li, Xinyu Zhang, Zhang Zhang, Peng Zhang, Caifeng Shan, Jungong Han

ACM Transactions on Multimedia Computing Communications and Applications

DOI

2023

Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Network

Zhibo Tian, Xiaolin Zhang, Peng Zhang, Kun Zhan

ACM International Conference on Multimedia (ACM MM)

DOI

2022

Dual-branch self-attention network for pedestrian attribute recognition

Zhenyu Liu, Zhang Zhang, Da Li, Peng Zhang, Caifeng Shan

Pattern Recognition Letters

DOI

2022

Improving Disentangled Representation Learning for Gait Recognition Using Group Supervision

Lingxiang Yao, Worapan Kusakunniran, Peng Zhang, Qiang Wu, Jian Zhang

IEEE Transactions on Multimedia

DOI

2021

Beyond modality alignment: Learning part-level representation for visible-infrared person re-identification

Peng Zhang, Qiang Wu, Xunxiang Yao, Jingsong Xu

Image and Vision Computing

DOI

精选作品

期刊论文

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models

MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction

WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction

Wan-Animate-2: Pushing the Application Boundaries of Character Animation

Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation

PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

A Lightweight Passive Depression Detection System Based on Interpretable Facial Feature Analysis

PSO-HEAD: Pseudo-Supervision Guided Spatial Optimization for View-Consistent 3D Full-Head Reconstruction

Cross-Domain Knowledge Transfer Learning With Macro-Expression Priors for Micro-Expression Recognition

Cross-scale gated embedding graph model for skeleton-based anomaly detection

基于视觉长短期记忆网络和双重注意力机制的微表情识别

Exploring Timeline Control for Facial Motion Generation

Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation

OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild

Co-speech Gesture Video Generation via Motion-Based Graph Retrieval

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model

MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation

MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody Animation

Controllable and Expressive One-Shot Video Head Swapping

ConsistencyTrack: A robust multi-object tracker with a generation strategy of consistency model

Implicit Feature Augmentation for Cloth-Changing Person Re-identification

Corruption-Invariant Person Re-Identification via Coarse-to-Fine Feature Alignment

Efficient abnormal behavior detection with adaptive weight distribution

Identity Semantic Correspondence for Cloth-Changing Person Re-Identification

Boosting Micro-Expression Recognition via Self-Expression Reconstruction and Memory Contrastive Learning

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

MaTe3D: Mask-Guided Text-based 3D-Aware Portrait Editing

VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior

DanceMeld: Unraveling Dance Phrases with Hierarchical Latent Codes for Music-to-Dance Synthesis

Pedestrian Attribute Recognition via Spatio-temporal Relationship Learning for Visual Surveillance

Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Network

Dual-branch self-attention network for pedestrian attribute recognition

Improving Disentangled Representation Learning for Gait Recognition Using Group Supervision

Beyond modality alignment: Learning part-level representation for visible-infrared person re-identification

会议论文

RGB-D SLAM Algorithm Based on Clustering and Geometric Residuals in Dynamic Environment

研究方向