Zhiyu ZHU (朱智宇)

Zhiyu ZHU (朱智宇)

Ph.D. candidate from Cityu HK

City University of Hong Kong

Biography

Zhiyu ZHU is a Ph.D. candidate of computer science at the Visual Information Processing Group Cityu HK, leaded by Dr. Junhui HOU . His research interests primarily lie in the field of computer vision, which covers both high-level and low-level topics, i.e., object detection and tracking, as well as image super-resolution and reconstruction. He has also published a number of papers in the prestigious conferences and journals, including, ICCV, NeurIPS, CVPR, ACM MM, TIP, TCI.

Download my resumé.

Interests
  • Computational Imaging
  • Object Tracking & Detection
  • Event Cameras
  • Hyperspectral Image Processing
  • Light Field Imaging
Education
  • Ph.D. in City University of Hong Kong

    2019-2023

  • M.S. in Harbin Institute of Technology

    2017-2019

  • B.Sc. in Harbin Institute of Technology

    2013-2017

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). Deep Diversity-Enhanced Feature Representation of Hyperspectral Images. submitted to TPAMI.

PDF Cite

(2022). Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution. TIP.

PDF Cite

(2022). GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation. submitted to IJCV.

PDF Cite

(2021). Learning spatial-angular fusion for compressive light field imaging in a cycle-consistent framework. ACM MM.

PDF Cite

(2021). Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild. ICCV 2021.

PDF Cite Code

(2021). WDA: an improved Wasserstein distance-based transfer learning fault diagnosis method. Sensors.

PDF Cite

(2021). CorrNet3D: Unsupervised End-to-End Learning of Dense Correspondence for 3D Point Clouds. CVPR 2021.

PDF Cite

(2021). Intelligent Fault Diagnosis Using Limited Data Under Different Working Conditions Based on SEflow Model and Data Augmentation. Advances in Intelligent Information Hiding and Multimedia Signal Processing.

PDF Cite

(2020). Hyperspectral Image Super-Resolution via Deep Progressive Zero-Centric Residual Learning. TIP.

PDF Cite Code

(2020). NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image. CVPR 2020 Workshop.

PDF Cite

(2020). When residual learning meets dense aggregation: Rethinking the aggregation of deep neural networks. arxiv.

PDF Cite

(2020). A novel deep learning method based on attention mechanism for bearing remaining useful life prediction. Applied Soft Computing.

PDF Cite

Contact