黄文炳

I am now an Assistant-Researcher/Shuimu-Tsinghua-Scholar at Tsinghua University, working with Prof. Fuchun Sun. I was a senior researcher at Tencent AI Lab from July 2017 to September 2019, where I had a chance of cooperation with Yu Rong, Tingyang Xu, Boqing Gong, Junzhou Huang, and Tong Zhang. I got my Ph.D. degree of computer science from Tsinghua University in July 2017, before which I studied Mathematics at Beihang University. I also spent one wonderful year (2016-2017) visiting ANU, supervised by Prof. Mehrtash Harandi. During my Ph.D. period, I have the honor of working with Deli Zhao, at Beijing Research Center, HTC.

My current research mainly lies in the areas of machine learning and computer vision, with particular focus on developing models/methods that analyze structured data (usually Non-Euclidean and Non-Grid alike) by, for example, characterizing invariance and equivariance among them. Those types of data that I have coped with include but are not limited to:

Graphs: graph representation learning, graph neural networks;

Videos: motion representation learning, event captioning, image2video translation, action classification and detection, imitation learning from videos;

Subspaces: infinite Grassmannian (modeled by linear dynamical systems);


News

[2020-05-18] Our proposal of tutorial "Advanced Deep Graph Learning: Deeper, Faster, Robuster, and Unsupervised" has been accepted by KDD'20!

[2020-02-24] 2 papers (of 2 submissions) accepted by CVPR-2020!

[2020-01-11] 1 paper accepted by WWW-2020!

[2019-11-11] 3 papers accepted by AAAI-2020!

[2019-10-21] Becoming the Assistant-Researcher/Shuimu-Tsinghua-Scholar in Tsinghua University!

[2019-09-04] 1 paper accepted by NeurIPS-2019 (spotlight) !

[2019-07-23] 2 papers (out of 3 submissions) accepted by ICCV-2019 (1 oral and 1 poster) !


Selected Publications on Graph Representation Learning (Please see my google-scholar for full reference)

(* denotes I am the corresponding author or the co-first author)

Yu Rong, Wenbing Huang*, Tingyang Xu, Junzhou Huang,

DropEdge: Towards Deep Graph Convolutional Networks for Node Classification,

International Conference on Representaion Learning (ICLR), Addis Ababa, Ethiopia, 2020


Zhen Peng, Wenbing Huang*, Minnan Luo, Qinghua Zheng, Yu Rong, Tingyang Xu and Junzhou Huang,

Graph Representation Learning via Graphical Mutual Information Maximization,

International World Wide Web Conference (WWW), Taibei, China, 2020.


Tian Bian, Xi Xiao, Tingyang Xu, Peilin Zhao, Wenbing Huang, Yu Rong, Junzhou Huang,

Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks

The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 2020.


Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Wenwu Zhuy, Junzhou Huang,

A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models,

The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 2020.


Runhao Zeng, Wenbing Huang*, Mingkui Tan#, Yu Rong, Peilin Zhao, Junzhou Huang, Chuang Gan,

Graph Convolutional Networks for Temporal Action Localization,

International Conference on Computer Vision (ICCV), Seoul, Korea, 2019.


Jia Li, Yu Rong, Hong Cheng, Helen Meng, Wenbing Huang, Junzhou Huang,

Semi-Supervised Graph Classification: A Hierarchical Graph Perspective,

International World Wide Web Conference (WWW), San Francisco, USA, 2019.


Wenbing Huang, Tong Zhang, Yu Rong, Junzhou Huang.

Adaptive Sampling Towards Fast Graph Representation Learning,

Annual Conference on Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018.

code poster


Selected Publications on Imitation Learning

Chao Yang; Xiaojian Ma; Wenbing Huang*; Fuchun Sun*; Huaping Liu; Junzhou Huang; Chuang Gan.

Imitation learning from observations by minimizing inverse dynamics disagreement,

Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2019-12-10 to 2019-12-14. (Spotlight)


Mingxuan Jing; Xiaojian Ma; Wenbing Huang*; Fuchun Sun; Chao Yang; Bin Fang; Huaping Liu;

Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance,

AAAI Conference on Arti cial Intelligence (AAAI), New York, USA, 2020-2-7 to 2020-2-12. (Spotlight)


Mingxuan Jing , Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu.

Task transfer by preference-based cost learning,

The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), Honolulu, Hawaii, USA, 2019.


Selected Publications on Videos/Subspace/Sequential Data

Wenbing Huang*; Lijie Fan*; Mehrtash Harandi; Lin Ma; Huaping Liu; Wei Liu; Chuang Gan*;

Toward e cient action recognition: Principal backpropagation for training two-stream networks,

IEEE Transactions on Image Processing (TIP), 2019, 28(4):1773-1782.


Lijie Fan; Wenbing Huang*; Chuang Gan; Stefano Ermon; Boqing Gong; Junzhou Huang;

End-to-end learning of motion representation for video understanding,

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, 2018-6-18 to 2018-6-22. (Spotlight)


Xuguang Duan; Wenbing Huang*; Chuang Gan; Jingdong Wang; Wenwu Zhu; Junzhou Huang;

Weakly supervised dense event captioning in videos,

Annual Conference on Neural Information Processing Systems (NeurIPS), Montreal, Cananda, 2018-12-3 to 2018-12-8.


Wenbing Huang; Mehrtash Harandi; Tong Zhang; Lijie Fan; Fuchun Sun*; Junzhou Huang;

Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Dictionary Learning,

Annual Conference on Neural Information Processing Systems (NeurIPS), Long Beach, California, USA, 2017-12-4 to 2017-12-9.


Wenbing Huang; Fuchun Sun*; Lele Cao; Deli zhao; Huaping Liu; Mehrtash Harandi;

Sparse Coding and Dictionary Learning with Linear Dynamical Systems,

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, 2016-6-26 to 2016-7-1. (Oral)


Wenbing Huang; Lele Cao; Fuchun Sun*; Deli zhao; Huaping Liu; Shanshan Yu;

Learning Stable Linear Dynamical Systems using the Weighted Least Square Method,

International Joint Conference on Arti cial Intelligence (IJCAI), New York, USA, 2016-7-9 to 2016-7-16.


Others

Wenbing Huang; Deli Zhao; Fuchun Sun*; Huaping Liu; Edward Chang;

Scalable Gaussian Process Regression using Deep Neural Networks,

International Joint Conference on Arti cial Intelligence (IJCAI), Buenos Aires, Argentina, 2015-7-25 to 2015-7-31.


Codes and Tools

DropEdge: To make your model deeper? Link to code .

GMI: How to perform self-supervised learning on graphs? see here.

PGCN: The source code for structured action dection from videos. Link to code.

AS-GCN: A package for fast graph representation learning. The distributed version will come soon. Link to code .

TVNet: A package for end-to-end optical flow estimation. Link to code.

WSDEC: The code for Weakly Supervised Dense Event Captioning in Videos. Link to code.

LDS: A tool box for linear dynamical systems modeling. Link to code.


Academic Services (since 2019)

Session Chair: IJCAI 2019 session track “Video: Events, Activities and Surveillance

Tutor: KDD 2020 tutorial "Advanced Deep Graph Learning: Deeper, Faster, Robuster, and Unsupervised"

Organizer: ACMMM 2020 workshop "Human-centric multimedia analysis".

PC member: NeurIPS 2019-2020, ICML 2019-2020, ICLR 2021, CVPR 2019-2020, ICCV 2019, ECCV 2020, AISTATS 2019-2020, IJCAI 2019-2020, AAAI 2019-2020.

Reviewer of Journals: TPAMI, IJCV, TIP, TNNLS, TKDE, Neurocomputing.