Search

ZJU VAI
  • Home
  • Blog
  • Members
  • Publications
  • Projects
  • Talks
  • Contact
Avatar

Haozhe Feng

Personal Homepage

Interests

Biomedical Image Computing
Visualization

Latest

    DPVisCreator: Incorporating Pattern Constraints to Privacy-preserving Visualizations via Differential Privacy

    IEEE TVCG | IEEE Transactions on Visualization and Computer Graphics
    Data privacy is an essential issue in publishing data visualizations. However, it is challenging to represent multiple data patterns in …
    Jiehui Zhou , Xumeng Wang , Jason K. Wong , Huanliang Wang , Zhongwei Wang , Xiaoyu Yang , Xiaoran Yan , Haozhe Feng , Huamin Qu , Haochao Ying , Wei Chen
    PDF Code Video DOI

    Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

    NeurIPS | Proceedings of the Advances in Neural Information Processing Systems
    Modeling multivariate time series (MTS) is critical in modern intelligent systems. The accurate forecast of MTS data is still …
    Yijing Liu , Qinxian Liu , Jianwei Zhang , Haozhe Feng , Zhongwei Wang , Zihan Zhou , Wei Chen
    PDF

    ChartNavigator: An Interactive Pattern Identification and Annotation Framework for Charts

    IEEE TKDE | IEEE Transactions on Knowledge and Data Engineering
    Patterns in charts refer to interesting visual features or forms. Identifying patterns not only helps analysts understand the …
    Tianye Zhang , Haozhe Feng , Wei Chen , Zexian Chen , Wenting Zheng , Xiaonan Luo , Wenqi Huang , Anthony Tung
    PDF Video Suppl.

    SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations

    AAAI | Proceedings of the AAAI Conference on Artificial Intelligence
    Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO …
    Haozhe Feng , Kezhi Kong , Minghao Chen , Tianye Zhang , Minfeng Zhu , Wei Chen
    PDF Code

    KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation

    ICML | Proceedings of the Thirty-eighth International Conference on Machine Learning
    Conventional unsupervised multi-source domain adaptation (UMDA) methods assume all source domains can be accessed directly. This …
    Haozhe Feng , Zhaoyang You , Minghao Chen , Tianye Zhang , Minfeng Zhu , Fei Wu , Chao Wu , Wei Chen
    PDF Code
Cite
Copy Download