Xiaolong ZHU (朱曉龍)

Starting from applications related to hand detection and posture analysis, I love to solve real-world problems with economic, explainable and reproducible solutions.

At Parametrix.ai


Redefine the relationship between AI and Human Players 2019 ~


What is the difference between AIs and living beings, if they have similar intellectural levels, or AIs are even smarter?

At Tencent


Active User and Developer of FeatherCNN 2018

Tencent TEG Group x 腾讯微视

FeatherCNN is a lightweight and fast inference framework for Arm Neon CPUs.


Go AI FineArt 2018

Tencent TEG Group

Train our AI, FineArt (绝艺), who masters the game of Go.

QQ 高能舞室

Pose Estimation for Mobile QQ Dec. 2017

Tencent TEG Group x QQ Mobile

Real-time skeleton tracking and action recognition on iOS and Android smart phones shipped since 2014.

Video Style Transfer

Live Video Style Transfer Mar. 2017

Tencent TEG Group x QQ Mobile

Image filters for live video style transfer on iOS and Android smart phones.

Chinese New Year H5

Chinese New Year H5 Jan. 2017

Tencent TEG Group

A filter that changes your photo background with Chinese New Year greetings.

Your Name

Your Name Oct. 2016

Tencent TEG Group x PTu

An interesting content-aware photo filter.

Neural Style Photo Filter

Neural Style Photo Filter Mar. 2016

Tencent TEG Group x PTu

Neural style photo filter is possible in Milliseconds!


Distributed Learning System Aug. 2015 to Mar. 2016

Tencent TEG Group

I develop algorithms for distributed training of acoustic models.

Ph. D. Study

End-to-end hand detection

End-to-end Hand Detection Mar. 2015 to Aug. 2015

Xiaolong Zhu, Wei Liu, Xuhui Jia and Kwan-Yee K. Wong
WACV 2016 Dataset is available upon request.

Now the end-to-end hand detection is possible via multi-task learning for CNN.

pixel-level hand detection

Pixel-level Hand Detection Jan. 2014 to Mar. 2015

Xiaolong Zhu, Xuhui Jia and Kwan-Yee K. Wong
ACCV 2014 CVIU 2015 Dataset is available upon request.

Pixel level hand detection using structured forests. It is very efficient and robust.

image search

Touch-based Image Search for Mobile ScenarioJun. 2013 to Aug. 2013

Internship in Lenovo IVC Lab.

sketch a hand

Sketch a Hand Shape Recognizer Sep. 2012 to Sep. 2013

Xiaolong Zhu, Ruoxin Sang, Xuhui Jia and Kwan-Yee K. Wong
IVCNZ 2013 Dataset is available upon request.

Provide possibility to sketch a hand shape recognizer using a customized Boltzmann machine.


Gesture Recognition with Visual Feedback Jun. 2012 to Sep. 2012

Internship in MSRA HCI Group.

kernel descriptors

Hand Posture Recognition Jan. 2012 to Jul. 2012

Xiaolong Zhu and Kwan-Yee K. Wong
ICPR 2012 Dataset is available upon request.

Single frame hand posture recognition by kernel descriptor for efficient SVM prediction.

depth from refraction

Self-Calibrating Depth from Refraction Oct. 2010 to Apr. 2011

Zhihu Chen, Kwan-Yee K. Wong, Yasuyuki Matsushita, Xiaolong Zhu and Miaomiao Liu
ICCV 2011 IJCV 2013

Obtain the depth of the image by refraction. Easy setup, promising results!

Undergraduate Study


Internship in Youdao.com Jun. 2010 to Aug. 2010

Front-end development for an LBS application.

range image

Autonomous Scene Labeling using LIDAR on a Car Oct. 2008 to Jul. 2010

Xiaolong Zhu, Huijing Zhao, Yiming Liu, Yipu Zhao and Hongbin Zha
IROS 2010 ICRA 2010

Semantic labelling for range data. Good segmentation is the key.

© Copyright 2010 by Xiaolong ZHU.