Hao Zhang (张皓)
|
|
Hao
Zhang (Chinese: 张皓; born Feb. 1994) Researcher Email
(change # to @): zhangh0214#gmail.com [知乎] [Google Scholar]
[GitHub] [LinkedIn] |
Biography
|
|
Since
2021, Hao is working as a researcher in Tencent
Video. Tencent Video is affiliated with the PCG (Platform &
Content Group), Tencent.
Tencent Video was officially launched in 2011. Until 2020, it has 123 million
paid members. The average daily usage time per user is 110 minutes. |
|
|
From
2019 to 2021, Hao was working as a researcher in YouTu Lab, founded
by Yunsheng Wu and professor Jiaya Jia (IEEE Fellow). The current leader is Yunsheng Wu. YouTu Lab is
affiliated with the CSIG
(Cloud and Smart Industries Group), Tencent. YouTu Lab is one of the three AI research labs in
Tencent, which focuses on computer vision. This team is sound for intelligent
video understanding, review, editing, etc. This team is severing several
internal products in Tencent, such as WeChat Top Stories (微信看一看),
Tencent Kandian (腾讯看点),
and Tencent WeSee (腾讯微视).
|
|
|
Before
that, Hao received his M.Sc.'s degree at LAMDA Group, which is led by
professor Zhi-Hua Zhou (foreign
member of the Academy of Europe, ACM/AAAI/AAAS/IEEE/IAPR Fellow). His adviser
was professor Jianxin Wu (member of
the Thousand Talents Plan). LAMDA (Learning And Mining from DatA) is affiliated with the National Key Laboratory for Novel
Software Technology, Department of
Computer Science and Technology and the School
of Artificial Intelligence, Nanjing
University (NJU), China. He received his B.Sc.'s degree in Nanjing
University in 2016. His
GPA ranked No.1 during his undergraduate studies. In the same year, he was
admitted to study for a M.Sc.'s degree without entrance examination. He was a
member of Excellent
Engineer Training Program, from Ministry
of Education of China. This
link provides a short interview of Hao. |
|
|
Besides,
he has been a member of Communist Party
of China since 2013. He is a columnist/writer of serval medias, such
as 机器之心,
新智元,
AI科技评论,
人工智能头条,
SIGAI, and AI100. |
Research Interests
|
|
Hao's
current research interests mainly include machine learning, computer
vision, especially on deep learning and visual recognition.
He is working on exploiting convolutional features in both supervised and
unsupervised ways to improve the efficiency of convolutional neural networks. |
|
|
Besides,
he is particularly interested in linear algebra and its applications.
Linear algebra is closely related to real-world applications, such as linear
systems (Ax = b), dynamic systems (uk+1
= Auk or du(t)/dt = Au(t)),
optimization problems (argminu f(u)),
linear transformations (T(u) = Au), etc.
Please refer to this page for
further discussions. |
Publications
|
|
吴建鑫著.
罗建豪,
张皓译.
吴建鑫审校.
模式识别.
机械工业出版社,
ISBN: 9787111643890, 1-368, 2020. [简介和勘误] [京东链接] [当当链接] |
|
|
张皓编著. 深度学习视频理解. 电子工业出版社, ISBN: 9787121419805, 1-314, 2021. [简介和勘误] [京东链接] [当当链接] |
|
|
|
|
|
Jian-Hao
Luo, Hao Zhang, Hong-Yu Zhou, Chen-Wei Xie, Jianxin Wu, and Weiyao Lin. ThiNet: Pruning CNN
filters for a thinner net. IEEE Transactions on Pattern Analysis and
Machine Intelligence (TPAMI), 41(10): 2525-2538, 2019. [pdf]
[code] |
|
|
Chen-Lin
Zhang, Hao Zhang, Xiu-Shen Wei, and Jianxin Wu. Deep
bimodal regression for apparent personality analysis. In Proceedings of
the 14th European Conference on Computer Vision (ECCV'16) Workshops, LNCS
9915, pages 311-324, 2016. [pdf]
[project page]
[slides]
[code] |
|
|
Xiu-Shen
Wei, Chen-Lin Zhang, Hao Zhang, and Jianxin
Wu. Deep
bimodal regression of apparent personality traits from short video sequences.
IEEE Transactions on Affective Computing (TAC), 9(3): 303-315, 2018. [pdf]
[project page]
[code] |
|
|
Hao
Zhang and Jianxin
Wu. A survey
on unsupervised image retrieval using deep features. Journal of Computer
Research and Development (CRAD), 55(9): 1829-1842, 2018. [pdf]
(in Chinese) |
|
|
Hao
Zhang and Jianxin
Wu. Ensemble max-pooling: Is only the maximum activation useful when pooling.
In Proceedings of CCF Conference on Artificial Intelligence (CCFAI), 2017. [pdf]
[poster]
[spotlight]
(acceptance rate: 34.0%) (in Chinese) |
|
|
Hao
Zhang and Jianxin
Wu. Ensemble
max-pooling: Is only the maximum activation useful when pooling. Journal of
University of Science and Technology of China (JUST), 47(10): 799-807, 2017.
[pdf]
(in Chinese) |
Awards and Honors
|
Four-Star
Distinguished Staff (Twice) |
Tencent |
2019,
2021 |
|
Company-level
Technology Breakthrough Award |
Tencent |
2019 |
|
YouTu
“Willing to Share” Award |
Tencent |
2020 |
|
YouTu
YouTech Preacher |
Tencent |
2020 |
|
ECCV |
2016 |
|
|
National
Scholarship |
Ministry
of Education of China |
2013 |
|
Member
of Excellent Engineer Training Program |
Ministry
of Education of China |
2013--2016 |
|
Excellent
All-round Student |
Jiangsu
Provincial Department of Education |
2015 |
|
Top-grade
in Jiangsu Provincial Undergraduate Electronics Design Contest |
Jiangsu
Committee of the National Undergraduate Electronics Design Contest |
2014 |
|
Top-grade
"Red Sun" Scholarship (only 20/12,000 undergraduate students in NJU
achieved per year) |
Nanjing
Red Sun CO., LTD |
2014 |
|
Top-grade
Graduate Research Scholarship |
Nanjing
University |
2016--2018
|
|
Excellent
Students |
Nanjing
University |
2014 |
|
Excellent
Cadre of Students |
Nanjing
University |
2013 |
|
Excellent
Undergraduate Student |
Nanjing
University |
2016 |
|
People's
Scholarship Speciality Specialization |
Nanjing
University |
2015 |
|
People's
Scholarship Social Work Specialization |
Nanjing
University |
2014 |
|
Second
Class Xingquan Responsibility Scholarship |
Nanjing
University |
2015 |
|
Excellent
League Member (twice) |
Youth
League Committee of Nanjing University |
2014,
2015 |
|
Excellent
Student in Summer Social Practice |
Youth
League Committee of Nanjing University |
2013 |
Articles
|
|
深度学习 n
三次简化一张图：一招理解LSTM/GRU门控机制
[link] (repost on 机器之心, AI100, 搜狐, 网易,
机器学习研究组订阅) n 深度学习基础（基本概念、优化算法、初始化、正则化等）
[link] (repost on 新智元, 搜狐) n
计算机视觉四大基本任务（分类、定位、检测、分割）
[link] (repost on 新智元,
搜狐, 新机器视觉,
矩视智能,
深度学习自然语言处理,
小白学视觉,
etc) n
计算机视觉其他应用（网络压缩、视觉问答、可视化、风格迁移等）
[link] (repost on 新智元,
人工智能头条,
人工智能学家,
前沿技术研究,
中国指挥与控制学会,
etc) n
双线性汇合（Bilinear Pooling）在细粒度图像分析及其他领域的进展综述
[link] (repost on SIGAI) n
深度学习项目实践技巧指南 [link] (repost on SIGAI, AI算法与图像处理) n
视频理解近期研究进展 [link] (repost on 新智元,
搜狐) n
动作识别时序汇合（Temporal
Pooling）方法介绍 [link] (repost
on 人工智能前沿讲习) n
YouTube推荐系统算法梳理
[link] (repost on 腾讯优图AI开放平台,
深度传送门,
智能推荐系统,
小小挖掘机,
etc) n
工业界视频理解解决方案大汇总 [link] (repost on 人工智能前沿讲习) |
|
|
机器学习
(repost on AI科技评论) n
人工智能科普文：AI的过去和现在 [link] n 第一章：绪论
[pdf] n 第二章：学习理论
[pdf] n 第三章：模型评估
[pdf] n 第四章：概率方法
[pdf] n 第五章：支持向量机
[pdf] n 第六章：集成学习
[pdf] n 第七章：决策树
[pdf] n 附录（机器学习数学基础速查手册）：线性代数
[pdf],
概率论
[pdf] n 当你在应用机器学习时你应该想什么
[link] (repost on AI100,
开发者头条, 搜狐) |
|
|
开发工具 n PyTorch
Cookbook (常用代码段整理合集)
[link]
(repost on 机器之心,
AI有道,
雷课,
极市平台,
AI派,
DeeAo大数据,
深度学习这件小事,
AI算法修炼营,
etc) n Python
加速运行技巧
[link] (repost on 极市平台,
机器学习算法那些事,
马哥Linux运维) n 论文格式排版你真的做对了吗?
常用格式及其LaTeX书写方法介绍
[link] (repost on 机器之心,
搜狐, 凤凰网科技, 新浪,
极客头条) |
|
|
A
simple and efficient implementation of im2col in convolution neural networks
[pdf] |
|
|
在电子,你会被加哪些技能点--电子学院专业课程分析
[pdf] |
|
|
停机问题(C语言版)
[link] |
|
|
Notes n
Notes on machine
learning [pdf] n
Notes on mathematics
for computer science [pdf] Notes
on C++: Concepts and practices [pdf] |
MOOC and Online Courses
Hao
is determined to become a lifelong learner. The followings are the courses he
completed.
|
|
n
John Guttag. 6.00:
Introduction to computer science and programming. MIT, 2011. n
Dennis Freeman. 6.01:
Introduction to electrical engineering and computer science I. MIT, 2011. n
Erik Demaine and Srinivas Devadas. 6.006:
Introduction to algorithms. MIT, 2011. n
Charles Leiserson and Erik Demaine. 6.046:
Introduction to algorithms. MIT, 2005. n
John Tsitsiklis. 6.041:
Probabilistic systems analysis and applied probability. MIT, 2013. n
Tom Leighton and Marten
van Dijk. 6.042:
Mathematics for computer science. MIT, 2010. n
Albert Meyer and Adam Chlipala. 6.042:
Mathematics for computer science. MIT, 2015. n
Erik Demaine, Srinivas Devadas, and Nancy Lynch. 6.046:
Design and analysis of algorithms. MIT, 2015. n
Sarina Canelake. 6.189:
A Gentle introduction to programming using Python. MIT, 2011. n
David Jerison. 18.01:
Single variable calculus. MIT, 2010. n
Denis Auroux. 18.02:
Multi-variable calculus. MIT, 2010. n
Jeremy Orloff and
Jonathan Bloom. 18.05:
Introduction to probability and statistics. MIT, 2014. n
Gilbert Strang. 18.06:
Linear algebra. MIT, 2011. |
|
|
n
Chris Manning and
Richard Socher. CS224n: Natural language
processing with deep learning. Stanford. n
Andrew Ng. CS229: Machine learning.
Stanford. n
Anand Avati. CS229:
Machine learning. Stanford. n
Andrew Ng and Kian Katanforoosh. CS230:
Deep learning. Stanford. n
Fei-Fei Li, Justin
Johnson, and Serena Yeung. CS231n:
Convolutional neural networks for visual recognition, Stanford. n
Div
Garg, Chetanya Rastogi, Advay
Pal, and Chris Manning. CS25:
Transformers united, Stanford. n
Andrew Ng et al. UFLDL: Deep learning tutorial.
Stanford. |
|
|
n
Michael
Fitzpatrick. Introduction to programming
with MATLAB. Vanderbilt University. [Grade: 100%] [Statement
of Accomplishment (with distinction)] n
Hsuan-Tien
Lin. Machine learning
foundations. National Taiwan University. [Grade: 96.4%] [Certificate
(with distinction)] n
Hsuan-Tien
Lin. Machine learning
techniques. National Taiwan University. [Grade: 96.0%] [Certificate
(with distinction)] n
Andrew Ng. Machine
learning. Stanford. [Grade: 100%] [Older
version] n
Andrew Ng. Neural
networks and deep learning. deeplearning.ai, 2017. n
Andrew Ng. Improving deep
neural networks: Hyperparameter tuning, regularization and optimization.
deeplearning.ai, 2017. n
Andrew Ng. Structuring
machine learning projects. deeplearning.ai, 2017. n
Andrew Ng. Convolutional
neural networks. deeplearning.ai, 2017. n
Andrew Ng. AI for everyone.
deeplearning.ai, 2019 n
Guillermo Sapiro. Image
and video processing from Mars to Hollywood with a stop at the hospital.
Duke University. [Solution Code] n
陈昌凯. 心理学与生活. Nanjing
University. n
吕世浩. 中国古代历史与人物---秦始皇.
National Taiwan University. n
吕世浩. 史記（一）. National Taiwan
University. |
Book List
The
followings are the books Hao has read.
n
Sheldon Axler. Linear algebra done right. Springer, 1997.
n
Stephen Boyd and Lieven Vandenberghe. Introduction to applied linear algebra:
Vectors, matrices, and least squares. Cambridge University Press, 2018.
n
Thomas Cormen, Charles Leiserson, Ronald
Rivest, and Clifford Stein. Introduction to algorithms (3rd edition). MIT
Press, 2009. [Solutions]
n
Allen Downey, Jeffrey Elkner, and Chris Meyers. How to think like a computer
scientist: Learning with Python. Green Tea Press, 2002.
n
Allen Downey. Think
Python: how to think like a computer scientist. Green Tea Press, 2012. [Online book]
n
Ian Goodfellow, Aaron
Courville, and Yoshua Bengio.
Deep Learning: Adaptive computation and machine learning series. MIT Press.
2016.
n
Rafael Gonzalez, Richard
Woods, and Steven Eddin. Digital image processing.
Pearson, 2007.
n
Rafael Gonzalez, Richard
Woods, and Steven Eddin. Digital image processing
using MATLAB. Gatesmark Publishing, 2009.
n
David C. Lay. Linear
Algebra and Its Applications (Fifth Edition). Pearson, 2014.
n
Eric Lehman, Thomson
Leighton, and Albert Meyer. Mathematics for computer science (2010 version).
MIT, 2010.
n
Eric Lehman, Thomson
Leighton, and Albert Meyer. Mathematics for computer science (2017 version).
MIT, 2017.
n
Stanley Lippman.
Essential C++. Addison-Wesley Longman Publishing Co., Inc., 1999.
n
Stanley Lippman, Josée Lajoie, and Barbara Moo. C++ primer (5th edition).
Addison-Wesley Professional, 2012. [Errata] [Solution code]
n
Bradley Miller and David Ranum. Problem solving with algorithms and data structures
using Python. Franklin, Beedle & Associates Inc., 2006. [Online book]
n
Andrew Ng. Machine
learning yearning. Draft. 2018.
n
Williams Shotts. The linux command line: A complete introduction. No Starch
Press, 2012.
n
Gilbert Strang. Introduction
to linear algebra (Fourth Edition). Wellesley Cambridge Press, 2009.
n
Gilbert Strang. Linear
algebra and its applications (Fourth Edition). Academic Press, 2006.
n
刘金鹏. Linux入门很简单.
清华大学出版社,
2012.
n
吴军. 数学之美.
第二版.
人民邮电出版社,
2014.
n
王世江、鸟哥. 鸟哥的Linux私房菜:基础学习篇.
第3版.
人民邮电出版社,
2010.
n
周志华. 机器学习.
清华大学出版社,
2016. [勘误修订]
Reimplementations
Hao
has reimplemented several papers, some of which have been open sourced in his GitHub.
n
Yuchi Huang, Xiuyu Sun, Ming Lu, and Ming Xu. Channel-max, channel-drop
and stochastic max-pooling. In Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition (CVPR) Workshops, pages 9–17, 2015.
n
Yannis Kalantidis, Clayton Mellina, and
Simon Osindero. Cross-dimensional weighting for
aggregated deep convolutional features. In Proceedings of the European Conference
of Computer Vision (ECCV) Workshops, pages 685--701, 2016.
n
Tsung-Yu Lin, Aruni RoyChowdhury, and Subhransu Maji. Bilinear CNN models for fine-grained visual
recognition. In Proceedings of the IEEE International Conference on Computer
Vision (ICCV), pages 1449--1457, 2015.
n
Xiu-Shen
Wei, Chen-Lin Zhang, Yao Li, Chen-Wei Xie, Jianxin Wu, Chunhua Shen, and Zhi-Hua Zhou. Deep descriptor transforming for image
co-localization. In Proceedings of the International Joint Conference on
Artificial Intelligence (IJCAI), pages 3048--3054, 2017.
n
Haibing Wu and Xiaodong Gu. Max-pooling dropout for regularization of
convolutional neural networks. In Proceedings of the International Conference
on Neural Information Processing (ICNIP), pages 46--54, 2015.
n
Jian Xu, Cunzhao Shi, Cheng-Zuo Qi, Chunheng Wang, and Baihua Xiao.
Part-based weighting aggregation of deep convolutional features for image
retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence
(AAAI), pages 7436--7443, 2018.
Correspondence
|
|
https://haomood.github.io/homepage/
(Continue updating) http://lamda.nju.edu.cn/zhangh/
(Deprecated) |
