Chenxia Han (韩晨夏)

M.Phil. Student
Department of Computer Science and Engineering
The Chinese University of Hong Kong

Office: Rm 921, Ho Sin-Hang Engineering Building
Email: cxhan at

[Google Scholar][Github][CV]


I am currently pursuing my M.Phil. degree in Computer Science and Engineering at The Chinese University of Hong Kong under the guidance of Prof. Eric Lo. Prior to starting my graduate studies, I gained valuable experience by working in the algorithm team at TuSimple for a year, under the supervision of Dr. Naiyan Wang.

My research interest lies at the intersection of machine learning and systems. I am particularly drawn to simple yet effective ideas that can significantly impact the field.




More is Less — Byte-quantized models are faster than bit-quantized models on the edge
Pengfei Zhang, Chenxia Han, Eric Lo
BigData, 2022
[Paper] [Slides] [BibTex]

Everest: A Top-K Deep Video Analytics System
Ziliang Lai, Chris Liu, Chenxia Han, Pengfei Zhang, Eric Lo, Ben Kao
SIGMOD Demo, 2022 [Best Demo Paper Runner Up]
[Paper] [Code] [BibTex]

Top-K Deep Video Analytics: A Probabilistic Approach
Ziliang Lai, Chenxia Han, Chris Liu, Pengfei Zhang, Eric Lo, Ben Kao
SIGMOD, 2021
[Paper] [Video] [Code] [BibTex]

SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
Yuntao Chen, Chenxia Han, Yanghao Li, Zehao Huang, Yi Jiang, Naiyan Wang
JMLR, 2019
[Paper] [Code] [BibTex]

Mask Guided Knowledge Distillation for Single Shot Detector
Yousong Zhu, Chaoyang Zhao, Chenxia Han, Jinqiao Wang, Hanqing Lu
ICME, 2019
[Paper] [BibTex]
†: My Final Year Project.


Revisiting Feature Alignment for One-stage Object Detection
Yuntao Chen, Chenxia Han, Naiyan Wang, Zhaoxiang Zhang
arXiv:1908.01570, 2019
[Paper] [Code] [BibTex]

Teaching Experiences

Academic Services