I am a PhD student in UC Berkeley Vision Science, with a focus on computer vision. I am currently advised by Prof. Stella Yu. Previously I was a research intern at Sensetime. I received my B.E in Electronic Engineering from XJTU in 2018, where I worked with Prof. Jinjun Wang at Institute of Artificial Intelligence and Robotics.
Sur-Real: Frechet Mean and Distance Transform for Complex-Valued Deep Learning
Rudrasis Chakraborty, Jiayun Wang, Stella X. Yu.
PBVS (CVPR) 2019. [paper] [code]
This work develops a novel deep learning architecture for naturally complex-valued data, with improved results and only 10% of the parameters as the baseline model.
Large-scale Long-Tailed Recognition in an Open World
Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu.
CVPR 2019 Oral. [paper] [project] [code]
This work formally defines the problem of open long-tailed recognition (OLTR) as optimizing for the overall accuracy of a naturally-distributed dataset with the presence of open classes.
A Comparison of Visual Features used by Humans and Machines to Classify Wildlife
Zhongqi Miao, Kaitlyn M Gaynor, Jiayun Wang, Ziwei Liu, Oliver Muellerklein, Mohammad S Norouzzadeh, Alex McInturff, Rauri C K Bowie, Ran Nathon, Stella X. Yu, Wayne M. Getz.
BiorXiv 2018. [paper]
This work aims to interpret the concepts behind the convolutional neural networks (CNNs) in classifying wildlife.
Joint Embedding and Classification for SAR Target Recognition
Jiayun Wang, Patrick Virtue and Stella X. Yu.
arXiv 2017. [paper]
This work aims to address the overfitting problem in remote sensing image classification.
Point to Set Similarity Based Deep Feature Learning for Person Re-identification
Sanping Zhou, Jinjun Wang, Jiayun Wang, Yihong Gong and Nanning Zheng.
CVPR 2017. [paper] [code]
This work presents a novel metric learning method based on P2S similarity comparison for person re-identification.
Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
Jiayun Wang, Sanping Zhou, Jinjun Wang and Qiqi Hou.
Pattern Recognition. [paper] [arxiv] [code]
This work designs a dynamically adaptive loss function to overcome the drawbacks of conventional loss functions for person re-identification.
We use a hierarchical approach for long-term video prediction, aiming at estimating high-level structure in the input frame first, then predicting how that structure grows in the future.
Our robotic system (Baxter) is able to recognize a number unique objects on the workspace and move them to their desired positions with relatively low rates of failure.