Xinyu Zhang

The Australian Institute for Machine Learning (AIML), University of Adelaide

XinyuZhang.jpg

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 and Prof. Anton van den Hengel.

Previously, I was a Senior Research Scientist 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.

:bulb:Research Topics

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:

  • Generative AI models: Image/Video generation/editing
  • Foundation model pre-training: Foundation and human-centric pre-training
  • Self-supervised / un-supervised / semi-supervised learning
  • Object/Attribute detection/recognition; Image/Text-to-image retrieval

News

Jan, 2025 :blue_heart: Release one paper [SimulateMotion] on Training-free Video Generation for Motion Simulation
Jan, 2025 One paper titled [InCPL] is accepted by Pattern Recognition (PR) on Test-time prompt tuning
Jan, 2025 Serving as Senior Program Committee Member (SPC) in IJCAI-25
Dec, 2024 I will serve as Area Chair in ICCV-25
Sep, 2024 :green_heart: One paper [DEVIL] is accepted by NeurIPS 2024 on Text-to-Video Generation for the dynamic evaluation
Feb, 2024 One paper [VRP-SAM] is accepted by CVPR 2024 on Efficient reference image based object segmentation
Oct, 2023 :yellow_heart: One paper [CAE v2] is accepted by TMLR 2023 on Large-sclae Self-superivised Pretraining
Oct, 2023 One paper [STAT] is accepted by TMM on Multi-Object Tracking
Sep, 2023 :orange_heart: One paper [HAP] is accepted by NeurIPS 2023 on human structure prior based Human-centric Pretraining
Jul, 2023 :heart: One paper [UniPT] is accepted by ICCV 2023 on Large-scale Image-Text Pretraining for Person Re-ID

Papers (📖 Full list)

  1. arXiv
    SimulateMotion.gif
    Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss
    Xinyu Zhang, Zicheng Duan, Dong Gong, and Lingqiao Liu
    arXiv preprint arXiv:2501.07563, 2025
  2. TMLR
    CAEv2.jpg
    CAE v2: Context autoencoder with CLIP latent alignment
    Xinyu Zhang, Jiahui Chen, Junkun Yuan, Qiang Chen, and 7 more authors
    Transactions on Machine Learning Research, 2023
  3. CVPR
    CVPR22.png
    Implicit sample extension for unsupervised person re-identification
    Xinyu Zhang, Dongdong Li, Zhigang Wang, Jian Wang, and 4 more authors
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022
  4. NeurIPS
    DEVIL.png
    Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
    Mingxiang Liao*, Hannan Lu*Xinyu Zhang*, Fang Wan, and 5 more authors
    In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
  5. NeurIPS
    HAP.jpeg
    Hap: Structure-aware masked image modeling for human-centric perception
    Junkun Yuan*Xinyu Zhang*†, Hao Zhou, Jian Wang, and 7 more authors
    Advances in Neural Information Processing Systems, 2023
  6. AAAI
    AAAI21.png
    Diverse knowledge distillation for end-to-end person search
    Xinyu Zhang, Xinlong Wang, Jia-Wang Bian, Chunhua Shen, and 1 more author
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2021
  7. ICCV
    ICCV19.png
    Self-training with progressive augmentation for unsupervised cross-domain person re-identification
    Xinyu Zhang, Jiewei Cao, Chunhua Shen, and Mingyu You
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019
  1. PR
    PR25.jpg
    Context-aware prompt learning for test-time vision recognition with frozen vision-language model
    Junhui Yin, Xinyu Zhang, Lin Wu, and Xiaojie Wang
    Pattern Recognition, 2025
  2. CVPR
    CVPR24.jpg
    VRP-SAM: SAM with visual reference prompt
    Yanpeng Sun, Jiahui Chen, Shan Zhang, Xinyu Zhang, and 5 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
  3. ICCV
    ICCV23.png
    Unified pre-training with pseudo texts for text-to-image person re-identification
    Zhiyin Shao*Xinyu Zhang*, Changxing Ding, Jian Wang, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
  4. TIP
    TIP23.jpg
    A real-time memory updating strategy for unsupervised person re-identification
    Junhui Yin, Xinyu Zhang, Zhanyu Ma, Jun Guo, and 1 more author
    IEEE Transactions on Image Processing, 2023
  5. TIP
    STAT.gif
    STAT: Multi-object tracking based on spatio-temporal topological constraints
    Junjie Zhang, Mingyan Wang, Haoran Jiang, Xinyu Zhang, and 2 more authors
    IEEE Transactions on Multimedia, 2023
  6. ACMMM
    ACMMM22.png
    Learning granularity-unified representations for text-to-image person re-identification
    Zhiyin Shao, Xinyu Zhang, Meng Fang, Zhifeng Lin, and 2 more authors
    In Proceedings of the 30th acm international conference on multimedia, 2022
  7. ECCV
    ECCV22.jpg
    UFO: unified feature optimization
    Teng Xi, Yifan Sun, Deli Yu, Bi Li, and 7 more authors
    In European Conference on Computer Vision, 2022
  8. IJCAI
    IJCAI22.jpg
    Self-Guided Hard Negative Generation for Unsupervised Person Re-Identification.
    Dongdong Li, Zhigang Wang, Jian Wang, Xinyu Zhang, and 3 more authors
    In IJCAI, 2022
  9. TITS
    TITS20.png
    Part-guided attention learning for vehicle instance retrieval
    Xinyu Zhang, Rufeng Zhang, Jiewei Cao, Dong Gong, and 2 more authors
    IEEE Transactions on Intelligent Transportation Systems, 2020
  10. TITS
    TITS18.jpg
    An extended filtered channel framework for pedestrian detection
    Mingyu You, Yubin Zhang, Chunhua Shen, and Xinyu Zhang
    IEEE Transactions on Intelligent Transportation Systems, 2018
  11. arXiv
    AddSD.jpg
    Add-SD: Rational Generation without Manual Reference
    Lingfeng Yang*Xinyu Zhang*, Xiang Li, Jinwen Chen, and 6 more authors
    arXiv preprint arXiv:2407.21016, 2024
  12. arXiv
    LW_DETR.jpg
    LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
    Qiang Chen*, Xiangbo Su*Xinyu Zhang*, Jian Wang, and 7 more authors
    arXiv preprint arXiv:2406.03459, 2024
  13. arXiv
    zebin.jpg
    Are Image Distributions Indistinguishable to Humans Indistinguishable to Classifiers?
    Zebin You, Xinyu Zhang, Hanzhong Guo, Jingdong Wang, and 1 more author
    arXiv preprint arXiv:2405.18029, 2024
  14. arXiv
    Arcana.jpg
    Improving multi-modal large language model through boosting vision capabilities
    Yanpeng Sun, Huaxin Zhang, Qiang Chen, Xinyu Zhang, and 4 more authors
    arXiv preprint arXiv:2410.13733, 2024
  15. arXiv
    MEM.jpg
    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 arXiv:2001.04123, 2020

Services

Area Chair, ICCV 2025

Senior Program Commitee Members, IJCAI 2025

Program Commitee Members, ICLR, ICML, NeurIPS, CVPR, ICCV, AAAI, IJCAI, ACMMM, ECCV

Journal Reviewer, IEEE TPAMI, IJCV, IEEE TIP, TOMM, IEEE TNNLS, TMM, PR, Neurocomputing

Session Member, Award panel member in Sydney AI meetup 2024

Teaching

2020, S2 - Guest Lecturer, COMP SCI 3314: Introduction to Statistical Machine Learning, The University of Adelaide

2019, S2 - Guest Lecturer, COMP SCI 3314: Introduction to Statistical Machine Learning, The University of Adelaide

2016, S1 - Teaching Assistant, 2080387: Pattern Recognition, Tongji University

2015, S2 - Teaching Assistant, 2080214: Machine Vision, Tongji University