Xinyu Zhang

Xinyu Zhang

Australian Institute for Machine Learning - Projects

Faculty of Sciences, Engineering and Technology

Eligible to supervise Masters and PhD (as Co-Supervisor) - email supervisor to discuss availability.

Dr Xinyu Zhang is currently a Research Fellow at Australian Institute for Machine Learning (AIML), the University of Adelaide (UoA), working with A/Prof. Lingqiao Liu. Before that, She was a Senior Research Scientist in Baidu Inc., working closely with Chief Scientist Jingdong Wang. She was also a Research Fellow at AIML working on the Neonatal Medical Project. She earned her Ph.D from Tongji University and was a visiting 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. Dr Zhang has broad interests in computer vision and metric learning. Her current research topics centers on image / video generation, self-supervised / un-supervised learning, human-centric AI and multimodal retrieval.

Google Scholar: https://scholar.google.com/citations?user=PSzJxD8AAAAJ&hl=en

Conference Reviewer:
ICLR, NeurIPS, CVPR, ICCV, ECCV, AAAI, IJCAI

Journal Reviewer:
TPAMI, IJCV, TMM, PR, Neurocomputing

  • Appointments
    Date Position Institution name
    2024 - ongoing Research Fellow University of Adelaide
    2021 - 2024 Senior Research Scientist Baidu (China)

  • Education
    Date Institution name Country Title
    Tongji University China PhD
    University of Adelaide Australia Visiting PhD student

  • Journals
    Year Citation
    2024 Zhang, J., Wang, M., Jiang, H., Zhang, X., Yan, C., & Zeng, D. (2024). STAT: Multi-Object Tracking Based on Spatio-Temporal Topological Constraints. IEEE Transactions on Multimedia, 26, 4445-4457.
    DOI Scopus4
    2023 Yin, J., Zhang, X., Ma, Z., Guo, J., & Liu, Y. (2023). A Real-Time Memory Updating Strategy for Unsupervised Person Re-Identification. IEEE Transactions on Image Processing, 32, 2309-2321.
    DOI Scopus22 WoS1
    2023 Zhang, X., Chen, J., Yuan, J., Chen, Q., Wang, J., Wang, X., . . . Wang, J. (2023). CAE v2: Context autoencoder with CLIP latent alignment. Transactions on Machine Learning Research.
    2020 Zhang, X., Zhang, R., Cao, J., Gong, D., You, M., & Shen, C. (2020). Part-Guided Attention Learning for Vehicle Instance Retrieval. IEEE Transactions on Intelligent Transportation Systems, 23(4), 1-13.
    DOI Scopus30 WoS19
    2018 You, M., Zhang, Y., Shen, C., & Zhang, X. (2018). An Extended Filtered Channel Framework for Pedestrian Detection. IEEE Transactions on Intelligent Transportation Systems, 19(5), 1640-1651.
    DOI Scopus21 WoS16

  • Conference Papers
    Year Citation
    2024 Yuan, J., Zhang, X., Zhou, H., Wang, J., Qiu, Z., Shao, Z., . . . Wang, J. (2024). Hap: Structure-aware masked image modeling for human-centric perception. In NeurIPS Proceedings. Online: NeurIPS.
    2024 Sun, Y., Chen, J., Zhang, S., Zhang, X., Chen, Q., Zhang, G., . . . Li, Z. (2024). VRP-SAM: SAM with Visual Reference Prompt. In IEEE Xplore. Seattle WA, USA.
    2023 Shao, Z., Zhang, X., Ding, C., Wang, J., & Wang, J. (2023). Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV, 2023) (pp. 1-11). Online: IEEE.
    DOI
    2022 Li, D., Wang, Z., Wang, J., Zhang, X., Ding, E., Wang, J., & Zhang, Z. (2022). Self-Guided Hard Negative Generation for Unsupervised Person Re-Identification. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (pp. 1067-1073). Vienna: International Joint Conferences on Artificial Intelligence Organization.
    DOI
    2022 Zhang, X., Li, D., Wang, Z., Wang, J., Ding, E., Shi, J. Q., . . . Wang, J. (2022). Implicit Sample Extension for Unsupervised Person Re-Identification. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 2022-June (pp. 7359-7368). Online: IEEE.
    DOI Scopus88 WoS8
    2022 Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., & Ding, C. (2022). Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. In Proceedings of the 30th ACM International Conference on Multimedia (pp. 5566-5574). Online: ACM.
    DOI
    2022 Xi, T., Sun, Y., Yu, D., Li, B., Peng, N., Zhang, G., . . . Wang, J. (2022). UFO: Unified Feature Optimization. In European Conference on Computer Vision Vol. 13686 (pp. 472-488). Tel Aviv: Springer Science and Business Media Deutschland GmbH.
    DOI
    2021 Zhang, X., Wang, X., Bian, J. -W., Shen, C., & You, M. (2021). Diverse Knowledge Distillation for End-to-End Person Search. In THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE Vol. 35 (pp. 3412-3420). Virtual, Online: ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE.
    DOI Scopus31 WoS12
    2019 Zhang, X., Cao, J., Shen, C., & You, M. (2019). Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In Proceedings of the IEEE International Conference on Computer Vision Vol. 2019-October (pp. 8221-8230). online: IEEE.
    DOI Scopus237 WoS163

  • Preprint
    Year Citation
    2024 Yang, L., Zhang, X., Li, X., Chen, J., Yao, K., Zhang, G., . . . Yang, J. (2024). Add-SD: Rational Generation without Manual Reference.
    2024 You, Z., Zhang, X., Guo, H., Wang, J., & Li, C. (2024). Are Images Indistinguishable to Humans Also Indistinguishable to
    Classifiers?.
    2024 Liao, M., Lu, H., Zhang, X., Wan, F., Wang, T., Zhao, Y., . . . Wang, J. (2024). Evaluation of Text-to-Video Generation Models: A Dynamics Perspective.
    2024 Chen, Q., Su, X., Zhang, X., Wang, J., Chen, J., Shen, Y., . . . Wang, J. (2024). LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection.
    2024 Wang, Y., Su, X., Chen, Q., Zhang, X., Xi, T., Yao, K., . . . Wang, J. (2024). OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer.
Connect With Me
External Profiles