About Me

I am a Research Fellow at Australian Institute for Machine Learning (AIML), the University of Adelaide, founded by Centre for Augmented Reasoning (CAR). I am working closely with A/Prof. Lingqiao Liu.

Previously, I was a Senior Developer and Engineer in Baidu Inc., working closely with Chief Scientist Jingdong Wang. I earned my Ph.D from Tongji University and was a joint Ph.D student at the University of Adelaide, under the supervision of Prof. Chunhua Shen, Prof. Javen Qinfeng Shi, Prof. Anton van den Hengel and Prof. Mingyu You.

My research focuses on designing machine learning algorithms to understand and depict the real large-scale unstructured data, and generate and create the synthetic data to simulate the real world. Specifically, my research topics center on image / video generation, self-supervised / un-supervised / semi-supervised learning, human-centric AI and multimodal retrieval.

News

• [Jan 2025] Release one paper [SimulateMotion] on Training-free Video Generation for Motion Simulation
  
• [Jan 2025] Serving as Area Chair of ICCV 2025
• [Jan 2025] Serving as SPC of IJCAI 2025
• [Jan 2025] One paper titled [InCPL] is accepted by Pattern Recognition (PR) on test-time prompt tuning
  
• [Sep 2024] One paper [DEVIL] is accepted by NeurIPS 2024 on Text-to-Video Generation
  
• [July. 2024] Release one paper [DEVIL] on Text-to-Video Generation
  
• [July. 2024] Release one paper [Add-SD] on image generation
  
• [July. 2024] Release one paper [LW-DETR] with its variant [OVLW-DETR], a transformer-based real-time detection and open-vocabulary detection framework
  
• [Feb. 2024] One paper [VRP-SAM] is accepted by CVPR 2024 for few-show segmentation
  
• [Oct. 2023] One paper [CAE v2] is accepted by TMLR 2023 on Self-superivised Pretraining
  
• [Oct. 2023] One paper [STAT] is accepted by TIP on Multi-Object Tracking
  
• [Sep. 2023] One paper [HAP] is accepted by NeurIPS 2023 on Human-centric Pretraining
  
• [July. 2023] One paper [UniPT] is accepted by ICCV 2023 on Image-Text Pretraining for Person Re-ID
  
• [Apr. 2023] One paper is accepted by TIP on Unsupervised Person Re-ID
  
• [Jul. 2022] [UFO] is accepted by ECCV 2022 on Foundation Model
  
• [Jun. 2022] One paper [LGUR] is accepted by ACMMM 2022 on Text-to-Image Person Re-ID
  
• [Apr. 2022] One paper is accepted by IJCAI 2022 on Unsupervised Person Re-ID
  
• [Feb. 2022] One paper [ISE] is accepted by CVPR 2022 on Unsupervised Person Re-ID.
• [Sep. 2021] Defended my Ph.D. thesis successfully!
• [Dec. 2020] One paper is [DKD] accepted by AAAI 2021 on Person Search
  
• [Oct. 2020] One paper [PGAN] is accepted by TITS 2020 on Vechicle Re-ID
  
• [Jul. 2019] One paper [PAST] is accepted by ICCV 2019 on Unsupervised Domain Adaptation for Person Re-ID
  

Publications

^* Equal contribution; ⁺ Corresponding author

• Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss
  Xinyu Zhang, Zicheng Duan, Dong Gong, Lingqiao Liu
  [PDF]
• In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model
  Junhui Yin, Xinyu Zhang, Lin Wu, Xiaojie Wang
  Pattern Recognition (PR) 2025
  [PDF]
• Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
  Mingxiang Liao^*, Hannan Lu^*, Xinyu Zhang^*, Fang Wan, Tianyu Wang, Yuzhong Zhao, Wangmeng Zuo, Qixiang Ye⁺, Jingdong Wang
  NeurIPS 2024
  [PDF] [Pytorch Code]
• Add-SD: Add-SD: Rational Generation without Manual Reference
  Lingfeng Yang^*, Xinyu Zhang^*, Xiang Li, Jinwen Chen, Kun Yao, Gang Zhang, Errui Ding, Lingqiao Liu, Jingdong Wang, Jian Yang⁺
  Arxiv preprint
  [PDF] [Pytorch Code]
• OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer
  Yu Wang, Xiangbo Su, Qiang Chen, Xinyu Zhang, Teng Xi, Kun Yao, Errui Ding, Gang Zhang, Jingdong Wang
  Arxiv preprint
  [PDF] [Pytorch Code]
• LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
  Qiang Chen^*, Xiangbo Su^*, Xinyu Zhang^*, Jian Wang, Jiahui Chen, Yunpeng Shen, Chuchu Han, Ziliang Chen, Weixiang Xu, Fanrong Li, Shan Zhang, Kun Yao, Errui Ding, Gang Zhang, Jingdong Wang⁺
  Arxiv preprint
  [PDF] [Pytorch Code]
• CAE v2: Context Autoencoder with CLIP Latent Alignment
  Xinyu Zhang^*, Jiahui Chen^*, Junkun Yuan, Qiang Chen, Jian Wang, Xiaodi Wang, Shumin Han, Xiaokang Chen, Jimin Pi, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang⁺
  TMLR 2023
  [PDF] [Pytorch Code]
• HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
  Junkun Yuan^*, Xinyu Zhang^*+, Hao Zhou, Jian Wang, Zhongwei Qiu, Zhiyin Shao, Shaofeng Zhang, Sifan Long, Kun Kuang⁺, Kun Yao, Junyu Han, Errui Ding, Lanfen Lin, Fei Wu and Jingdong Wang⁺
  NeurIPS 2023
  [PDF] [Pytorch Code]
• Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification
  Zhiyin Shao^*, Xinyu Zhang^*, Changxing Ding⁺, Jian Wang and Jingdong Wang
  ICCV 2023
  [PDF] [Pytorch Code]
• STAT: Multi-Object Tracking Based on Spatio-Temporal Topological Constraints
  Junjie Zhang, Mingyan Wang, Haoran Jiang, Xinyu Zhang, Chenggang Yan, Dan Zeng⁺
  TIP 2023
  [PDF]
• A Real-time Memory Updating Strategy for Unsupervised Person Re-identification
  Junhui Yin, Xinyu Zhang, Zhanyu Ma⁺, Jun Guo, Yifan Liu
  TIP 2023
  [PDF]
• Implicit Sample Extension for Unsupervised Person Re-Identification
  Xinyu Zhang^*, Dongdong Li^*, Zhigang Wang, Jian Wang, Javen Qinfeng Shi, Zhaoxiang Zhang and Jingdong Wang⁺
  CVPR 2022
  [PDF] [Paddle Code] [Pytorch Code]
• Learning Granularity-Unified Representations for Text-to-Image Person Re-identification
  Zhiyin Shao, Xinyu Zhang, Meng Fang, Zhifeng Lin, Jian Wang, and Changxing Ding⁺
  ACMMM 2022
  [PDF] [Pytorch Code]
• Self-Guided Hard Negative Generation for Unsupervised Person Re-Identification
  Dongdong Li, Zhigang Wang, Jian Wang, Xinyu Zhang, Errui Ding, Jingdong Wang, Zhaoxiang Zhang⁺
  IJCAI 2022
  [PDF]
• UFO: Unified Feature Optimization
  Teng Xi, Yifan Sun, Deli Yu, Bi Li, Nan Peng, Gang Zhang, Xinyu Zhang, Zhigang Wang, Jinwen Chen, Jian Wang, Lufei Liu, Haocheng Feng, Junyu Han, Jingtuo Liu, Errui Ding, Jingdong Wang
  ECCV 2022
  [PDF]
• Diverse Knowledge Distillation for End-to-End Person Search
  Xinyu Zhang, Xinlong Wang, Jia-Wang Bian, Chunhua Shen and Mingyu You⁺
  AAAI 2021
  [PDF] [Pytorch Code]
• Part-Guided Attention Learning for Vehicle Instance Retrieval
  Xinyu Zhang^*, Rufeng Zhang^*, Jiewei Cao, Dong Gong, Mingyu You⁺ and Chunhua Shen
  IEEE Transactions on Intelligent Transportation Systems (TITS) 2020
  [PDF] [Pytorch Code]
• Self-Training with Progressive Augmentation for Unsupervised Cross-Domain Person Re-identification
  Xinyu Zhang^*, Jiewei Cao^*, Chunhua Shen⁺ and Mingyu You
  ICCV 2019
  [PDF] [Pytorch Code]
• Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory
  Xinyu Zhang, Dong Gong, Jiewei Cao and Chunhua Shen⁺
  Arxiv preprint
  [PDF]
• An extended filtered channel framework for pedestrian detection
  Mingyu You⁺, Yubin Zhang, Chunhua Shen and Xinyu Zhang
  IEEE Transactions on Intelligent Transportation Systems (TITS) 2018
  [PDF]

Professional Activities

• Conference Reviewer
  ICML, ICLR, NeurIPS, CVPR, ICCV, ECCV, AAAI, IJCAI
• Journal Reviewer
  TPAMI, IJCV, TOMM, TMM, PR, Neurocomputing