Biography
Dr. Hu Zhang (张虎) is currently a Postdoctoral Research Fellow at CSIRO, Australia. Before that, he was a Postdoctoral at EECS, The University of Queensland. His research interests include 3D LiDAR-based detection, 3D reconstruction, long-tailed classification, and computer vision based applications. He received his Ph.D. degree from University of Technology Sydney (UTS). He graduated from University of Science and Technology of China (USTC) and obtained his bachelor degree.
News
- Jan 2024: I joined CSIRO, Australia.
Preprints
-
OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection
Hu Zhang, Jianhua Xu, Tao Tang, Haiyang Sun, Xin Yu, Zi Huang, Kaicheng Yu
arXiv [PDF] -
BAVS: bootstrapping audio-visual segmentation by integrating foundation knowledge
Chen Liu, Peike Li, Hu Zhang, Lincheng Li, Zi Huang, Dadong Wang, Xin Yu
arXiv [PDF]
Publications
-
RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
MD Wahiduzzaman Khan*, Hongwei Sheng*, Hu Zhang*, Heming Du, Sen Wang, Minas Theodore Coroneo, Farshid Hajati, Sahar Shariflou, Michael Kalloniatis, Jack Phu, Ashish Agar, Zi Huang, Mojtaba Golzan, Xin Yu [*Equal]
NeurIPS 2023 [PDF] [Project page] -
Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics
Chen Liu, Peike Li, Xingqun Qi, Hu Zhang, Lincheng Li, Dadong Wang, Xin Yu
MM 2023 [PDF] -
Divide and Retain: A Dual-Phase Modeling for Long-Tailed Visual Recognition
Hu Zhang, Linchao Zhu, Xiaohan Wang, Yi Yang
TNNLS 2023 [PDF] -
Motion-excited sampler: Video adversarial attack with sparked prior
Hu Zhang, Linchao Zhu, Yi Zhu, Yi Yang
ECCV 2020 [PDF] -
Query-efficient meta attack to deep neural networks
Jiawei Du*, Hu Zhang*, Joey Tianyi Zhou, Yi Yang, Jiashi Feng [*Equal]
ICLR 2020 [PDF] -
Generalized Majorization-Minimization for Non-Convex Optimization
Hu Zhang, Pan Zhou, Yi Yang, Jiashi Feng
IJCAI 2019 [PDF]
Competitions
-
The first place on 8th workshop on Computer Vision in Plant Phenotyping and Agriculture, 2023, ICCV [Deep Nutrient Deficiency Track][PDF].