Welcome to visit Pichao Wang's Homepage!


                
PichaWang, PhD
DAMO Academy, Alibaba Group (U.S.) Inc.
Email: pichaowang@ gmail.com   Goolge Scholar ResearchGate

News:

I am recruiting Research Interns (PhD candidates) to join my research project @ Alibaba DAMO Academy. If you are interested in computer vision, especially transformer-based applications, and happens to be interested in Alibaba, please contact me.

Biography

 I am a senior algorithm engineer at DAMO Academy, Alibaba Group (U.S.) Inc. Before I joined Alibaba Group, I worked as a researcher at Motovis Inc. I received my Ph.D in Computer Science from University of Wollongong, Australia, in Oct. 2017, supervised by A/Prof. Wanqing Li and Prof. Philip Ogunbona  I received  my M.E. in Information and Communication Engineering from Tianjin University, China, in 2013, supervised by Prof. Yonghong Hou, and B.E. in Network Engineering from Nanchang University, China, in 2010.

Research Interests:

· Computer Vision · Deep Learning · Human Motion Analysis · Video Understanding


Selected Awards and Honors

12. Jul. 2020, ICME2020 Outstanding Reviewer Award

11. Jun. 2020, Second Prize, Multiple Object Tracking and Segmentation@CVPR2020 

10. May. 2018, EIS Faculty Postgraduate Thesis Award.

9. Dec. 2017, Journal of Visual Communication and Image Representation (outstanding reviewer, certificate)

8. Aug. 2017, Second Prize, Action, Gesture, and Emotion Recognition Workshop and Competitions: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions@ICCV2017

7. Apr. 2017 First Prize (Winner), Large Scale 3D Human Activity Analysis Challenge in Depth Video@ICME2017

6. Dec. 2016 Second Prize, Joint Contest on Multimedia Challenges Beyond Visual Analysis@ICPR2016

5. Dec. 2016 Third Prize, Joint Contest on Multimedia Challenges Beyond Visual Analysis@ICPR2016

4. Dec. 2016 ChaLearn Travel Grants@ICPR2016

3. Oct.  2015 ACM MM 2015 Student Travel Award

2. Jan. 2013 Excellent Postgraduate Award

1. Dec. 2011 Excellent Prize, National Campus CUDA Programming Contest. [certificate]

Publications:

Ph.D. Dissertation

Action Recognition from RGB-D Data. The University of  Wollongong, 2017. (Best Postgraduate Thesis Award) [link]

Conference Papers


23.  Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, and Wei Jiang,
"TransReid: Transformer-based Object Re-identification"
ICCV 2021

22. Min Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, and Rong Jin,
"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition"
ICCV 2021
 
21. Liang Han*, Pichao Wang*, Zhaozheng Yin, Fan Wang, and Hao Li, (* equal contribution)
"Exploiting Better Feature Aggregation for Video Object Detection",
ACM MM2020.

20.Jingkun Gao, Xiaomin Song, Qingsong Wen, Pichao Wang, Liang Sun and Huan Xu,
"RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks"
KDDW2020.

19.
 Chang Tang, Xinwang Liu, Xinzhong Zhu, En Zhu, Kun Sun, Pichao Wang, Lizhe Wang and Albert Zomaya,
"R2MRF: Defocus Blur Detection via Recurrently Refining Multi-scale Residual Features"
AAAI2020.

18. Xiangyu Li, Yonghong Hou, Qi Wu, Pichao Wang, and Wanqing Li,
"DVONet: Unsupervised Monocular Depth Estimation and Visual Odometry",
VCIP2019.

17. Xianzhe Xu, Yonghong Hou, Pichao Wang*, Zhongyu Jiang, and Wanqing Li, (Corresponding author)
"Light weight stereo matching via deep extraction and integration of low and high level information"
ICME2019. (Oral)

16. Renyi Xiao, Yonghong Hou, Zihui Guo, Chuankun Li, Pichao Wang, and Wanqing Li,
"Self-attention guided deep features for action recognition"
ICME2019.

15. Tang Chang, Xinwang Liu, Xinzhong Zhu, and Pichao Wang
"Salient Object Detection via Recurrently Aggregating Spatial Attention Weighted Cross-level Deep Features"
ICME2019.

14. Pichao Wang, Wanqing Li, Jun Wan, Philip Ogunbona, and Xinwang Liu,
"Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition"
AAAI2018. (Oral)[pdf][codes]

13.  Pichao Wang*, Shuang Wang*, Zhimin Gao, Yonghong Hou, and Wanqing Li, (* equal contribution)
"Structured Images for RGB-D Action Recognition "

12. Huogen Wang*, Pichao Wang*, Zhanjie Song, and Wanqing Li, (* equal contribution)
"Large-scale Multimodal Gesture Recognition Using Heterogeneous Networks "
ICCV2017.[pdf][codes]

11. Huogen Wang*, Pichao Wang*, Zhanjie Song, and Wanqing Li, (* equal contribution)
"
Large-scale Multimodal Gesture Segmentation and Recognition based on Convolutional Neural Network"
ICCV2017. [pdf][codes]

10. Pichao Wang, Wanqing Li, Zhimin Gao, Yuyao Zhang, Chang Tang, and Philip Ogunbona,
"Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks",
 CVPR2017.  [pdf] [codes]

9. Zewei Ding, Wanqing Li, Pichao Wang, Philip Ogunbona, and Ling Qin,
"Weakly Structured Information Aggregation for Upper-body Posture Assessment Using ConvNets",
ICME2017. [pdf] (oral)

8. Chuankun Li*,  Pichao Wang*,  Shuang Wang, Yonghong Hou and Wanqing Li, (* equal contribution)
"Skeleton-based Action Recognition Using LSTM and CNN",
in Large Scale 3D Human Activity Analysis Challenge in Depth Videos, ICMEW2017. [pdf] (rank the first place) [certificate]

7. Zewei Ding,  Pichao Wang*,  Philip Ogunbona, and Wanqing Li, (Corresponding author)
"Investigation of Different Skeleton Features for CNN-based 3D Action Recognition",
ICMEW2017. [pdf][codes]

 6. Pichao Wang, Wanqing Li, Song Liu, Yuyao Zhang, Zhimin Gao and Philip Ogunbona,
"Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks",
in ChaLearn Looking at People (LAP) Challenge, ICPR2016.  [pdf]  [codes] [certificate] (rank the third place)

5. Pichao Wang, Wanqing Li, Song Liu, Zhimin Gao, Chang Tang and Philip Ogunbona,
 "Large-scale Isolated Gesture Recognition Using Convolutional Neural Networks",
in ChaLearn
Looking at People (LAP) Challenge, ICPR2016.
[pdf] [codes] [certificate]  (rank the second place)

4. Jing Zhang, Wanqing Li, Pichao Wang, Philip Ogunbona, Song Liu and Chang Tang,
"A Large Scale RGB-D Dataset for Action Recognition",
 
UHA3DS workshop@ICPR2016. [pdf][dataset]

3.
Pichao Wang*, Zhaoyang Li*, Yonghong Hou  and Wanqing Li, (* denotes equally contributed)

"Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks"
ACM MM16.
[pdf] [codes]

2
Pichao WangWanqing LiZhimin GaoChang TangJing Zhang  and Philip Ogunbona,
"ConvNets-Based Action Recognition from Depth Maps Through Virtual Cameras and Pseudocoloring
"
ACM MM15. [pdf] [bib][poster] [codes]

1. Pichao Wang, Wanqing Li, Philip Ogunbona, Zhimin Gao and Hanling Zhang,

 "Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation"

DICTA2014. [pdf] [bib][poster] [codes]


Journal Articles

38. Liang Han*, Pichao Wang*, Zhaozheng Yin, Fan Wang, and Hao Li, (* equal contribution)
"Context and Structure Mining Network for Video Object Detection"
International Journal of Computer Vision, accepted on 13th July, 2021

37. Liang Han*, Pichao Wang*, Zhaozheng Yin, Fan Wang, and Hao Li, (* equal contribution)
"Class-aware Feature Aggregation Network for Video Object Detection"
IEEE Transactions on Circuits and Systems for Video Technology, accepted on 18th June, 2021

36. Zitong Yu, Xiaobai Li, Pichao Wang and Guoying Zhao,
"TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection"
IEEE Signal Processing Letters, accepted on 9th June, 2021.

35. Zitong Yu, Benjia Zhou, Jun Wan, Pichao Wang, Haoyu Chen, Xin Liu, Stan Z Li, and Guoying Zhao,
"Searching Multi-Rate and Multi-Modal Temporal Enhanced Network for Gesture Recognition"
IEEE Transaction on Image Processing, accepted on 25th May, 2021

34. Xiangyu Li, Yonghong Hou,  Pichao Wang, Zhimin Gao, Mingliang Xu, and Wanqing Li,(Corresponding author
"Trear: Tranformer-based RGB-D Egocentric Action Recognition",
 IEEE Transactions on Cognitive and Developmental System, accepted on 30th, Dec. 2020.

33. Xiangyu Li, Yonghong Hou,  Pichao Wang, Zhimin Gao, Mingliang Xu, and Wanqing Li,
"Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry",
 Neural Computing and Applications, accepted on 17th, Nov. 2020.

32. Haoyuan Zhang, Yonghong Hou, Pichao Wang*, Zihui Guo, and Wanqing Li, (Corresponding author)
"SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching"
Journal of Visual Communication and Image Representation, accepted on 9th, Oct,. 2020. [Code]

31. Zhiming Gao, Pichao Wang, Huogen Wang, Mingliang Xu, and Wanqing Li,
"A review of dynamic maps for 3D human motion recognition using ConvNets and its improvement"
Neural Processing Letters, accepted on 20th, July, 2020.

30. Huogen Wang, Zhanjie Song, Wanqing Li, and Pichao Wang,
"A Hybrid Network for Large-scale Action Recognition from RGB and Depth Modalities",
Sensors, accepted on 3rd, June, 2020.

29. Chang Tang, Xinwang Liu, Shan An, and Pichao Wang,
"BR2NET: Defocus Blur Detection via Bidirectional Channel Attention Residual Refining Network"
IEEE Transactions on Multimedia, Accepted on 16th March 2020.

28. Chuankun Li, Yonghong Hou, Wanqing Li, and Pichao Wang,
"Learning Attentive Dynamic Maps (ADMs) for Understanding Human Actions"
Journal of Visual Communication and Image Representation, Accepted on 8th Sep. 2019. 

27. Chang Tang, Meiru Bian, Xinwang Liu,Miaomiao Li, Hua Zhou,Pichao Wang, Hailin Yin,
"Unsupervised feature selection via latent representation learning and manifold regularization"
Neural Networks, Accepted on 22th April 2019

26. Chang Tang, Xinwang Liu, Pichao Wang, Changqing Zhang, Miaomiao Li and Lizhe Wang,
Adaptive Hypergraph Embedded Semi-supervised Multi-label Image Annotation
 IEEE Transactions on Multimedia, Accepted on 22th March 2019

25. Chang Tang, Xinzhong Zhu, Xinwang Liu, Miaomiao Li, Pichao Wang, Changqing Zhang and Lizhe Wang,
“Learning Joint Affinity Graph for Multi-view Subspace Clustering”
 IEEE Transactions on Multimedia, Accepted on 10th Dec. 2018

24. Chuankun Li, Yonghong Hou, Pichao Wang*, and Wanqing Li, (Corresponding author)
"Multi-view Based 3D Action Recognition Using Deep Networks",
IEEE Transactions on Human Machine Systems, accepted on 20th, Oct. 2018.

23. Chang Tang, Wanqing Li, Pichao Wang*, and Lizhe Wang, (*Corresponding author)
"Online Human Action Recognition Based on Incremental Learning of Weighted Covariance Descriptors"
Information Sciences, accepted on 1st Aug. 2018. [code]

22. Chang Tang, Jiajia Chen, Xinwang Liu, Miaomiao Li, Pichao Wang, Minhui Wang, Peng Lu, 
"Consensus Learning Guided Multi-view Unsupervised Feature Selection",
Knowledge-Based Systems, Accepted on 28th, Jun 2018.

21. Xinzhong Zhu, Chang Tang, Pichao Wang, Huiying Xu, Minhui Wang, Jie Tian, 
"Saliency Detection via Affinity Graph Learning and Weighted Manifold Ranking", 
Neurocomputing, accepted on 2 Jun. 2018.

20. Pichao Wang, Wanqing Li, Chuankun Li and  Yonghong Hou ,
"Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks"
Knowledge-Based Systems, Accepted on 21th, May 2018. [pdf][codes]

19. Pichao WangWanqing Li, Philip Ogunbona, Jun Wan and Sergio Escalera,
"RGB-D-based Human Motion Recognition with Deep Learning: A Survey ",
Computer Vision and Image Understanding, Accepted on 25th Apr. 2018.

18. Pichao WangWanqing LiZhimin Gao, Chang Tangand Philip Ogunbona,
 "Depth  Pooling Based Large-scale 3D Action Recognition with Deep Convolutional Neural Networks"
 IEEE Transactions on Multimedia, Accepted on 18th Mar. 2018.[pdf][codes]

17. 
Chang Tang, Xinwang Liu, Miaomiao Li, Pichao Wang*, Jiajia Chen, Lizhe Wang,  and Wanqing Li, (*Corresponding author)
"Robust Unsupervised Feature Selection via Dual Self-representation and Manifold Regularisation"
Knowledge-based Systems, Accepted on 4 Jan. 2018.

16. Yonghong Hou, Shuang Wang,  Pichao Wang*, Zhimin Gao, and Wanqing Li, (* Corresponding author)
"
Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition",
 IEEE Access, Accepted on 5 Dec. 2017. [codes]


15
Chang Tang, Xinzhong Zhu, Jiajia Chen, Pichao Wang, Xinwang Liu, Jie Tian, 
"Robust Graph Regularized Unsupervised Feature Selection"
Expert Systems With Applications, Accepted on 28 Nov, 2017.

14. Chuankun Li, Yonghong Hou, Pichao Wang*, and Wanqing Li, (*Corresponding author)
"Joint Distance Maps for Human Action Recognition with Convolutional Neural Networks"
,
IEEE Signal Processing Letters, Vol.  24, No. 5, pp. 624-628, May, 2017. [pdf][codes]

13. Yonghong Hou, Zhaoyang Li,  Pichao Wang* and Wanqing Li, (* Corresponding author)
"
Skeleton Optical Spectra Based Action Recognition Using Convolutional Neural Networks",

 IEEE Transactions on Circuits and Systems for Video Technology, Accepted on 8 Nov. 2016. [pdf][codes]

12. Pichao WangWanqing LiZhimin Gao, Jing Zhang,  Chang Tangand Philip Ogunbona,
 "Action Recognition from Depth Maps Using Deep Convolutional Neural Networks",  
 IEEE Transactions on Human Machine Systems, Vol. 46, No. 4, pp. 498-509, August, 2016. [pdf] [bib][codes]

11. Jing Zhang, Wanqing Li, Philip Ogunbona, Pichao Wang and Chang Tang, 
 "RGB-D based Action Recognition Datasets: A Survey",
Pattern Recognition,
Vol. 60, pp.86-105, Dec. 2016. [pdf] [bib]

10. Chang Tang, Pichao Wang,  Changqing Zhang,  and Wanqing Li,
"
Salient Object Detection via Weighted Low Rank Matrix Recovery",
IEEE Signal Processing Letters, Vol. 24, No. 4, pp. 490-494, April 2017.

9. Chang Tang, Jin Wu,Yonghong Hou, Pichao Wang and Wanqing Li,
"A spectral and spatial approach of coarse-to-fine blurred image region detection",
IEEE Signal Processing Letters, Vol. 23, No. 11, pp. 1652-1656, Sep. 2016.[paper] [codes]

8. Chang Tang, Chunping Hou, Yonghong Hou, Pichao Wang and  Wanqing Li,
"
An Effective Edge-preserving Smoothing Method for Image Manipulation",
Digital Signal Processing, Vol.63, pp.10-24, April 2017.[paper]

7. Chang Tang, Chunping Hou, Pichao Wang and Zhanjie Song, 
 "Salient object detection using color spatial distribution and minimum spanning tree weight",
 Multimedia Tools and Applications, Vol. 75, No.12, pp. 6963-6978, June 2016. [pdf] [bib]

6. Yonghong Hou, Pichao Wang, Wei Xiang, and Zhimin Gao, 
 “A Novel Rate Control Algorithm for Video Coding Based on Fuzzy-PID Controller”,
Signal, Image and Video Processing, 9 (4): 875-884, 2015. [pdf]

5. Pichao Wang, Lei You, Jing Tian, and Zhimin Gao, 
 “Word Document Decryption Based on GPU”,
 Information Technology,151-154, 04, 2013. 

4. Yonghong Hou, Pichao Wang, Wei Xiang, Xiaoming Zhao, Chunping Hou, 
“Ergodic Capacity Analysis of Spatially Modulated System”,
China Communications, Vol. 10, No.7,  pp. 118-125, July 2013. [pdf]

3. You Lei, Lei Jian-jun, and Wang Pichao,  
“Distributed Optimization Method for SVC Streaming in Wireless Multi-hop Networks”,
 Journal of Tianjin University, Vol. 46, No. 1, pp. 73-78, Jan. 2013.

2. Yonghong Hou, Zhimin Gao, Pichao Wang, and Chunping Hou,  
“PID-Based Bit Allocation Strategy in Asymmetric Stereoscopic Video Coding with Fuzzy Quality Controller”, 
Transations of Tianjin University,  19: 202-210, 2013.

1. Qing Wang, Hua Chen, Guohuang Zhao, Bin Chen, and Pichao Wang, 
“An Improved Direction Finding Algorithm Based on Toeplitz Approximation ”
,
Sensors, 13, 746-757, 2013. [pdf]



Academic Activities

Editorial Works:
1. Associate Editor, Computer Engineering(<<计算机工程>>, Chinese Journal), 2019-2024
2. Area Chair, ICME, 2021: Area Chair for Multimedia Analysis and Understanding (main area)

Selected Invited Journal Reviewer
1. IEEE Transactions on Image Processing (since 2016)
2. IEEE Transactions on Circuits and Systems for Video Technology (since 2016)
3. IEEE Signal Processing Letters (since 2016)
4. IEEE Transactions on Cybernetics (since 2017)
5. IEEE Transactions on Neural Networks and Learning Systems (since 2018)
6. IEEE Transactions on Industrial Information (since 2018)
7. IEEE Transactions on Audio, Speech and Language Processing (since 2018) 
8. IEEE Transactions on Multimedia (since 2019)
9. IEEE Internet of Things Journal (since 2020)
10. ACM Transactions on Interactive Intelligent Systems (since 2019)
11. ACM Transactions on Multimedia Computing, Communications and Applications (since 2019)
12. Pattern Recognition (since 2017)


Conference Technical Program Committee Member:
1. ICCV2017,2019
2. CVPR2018,2019,2020,2021
3. ICME2018,2019,2020,2021
4. IJCAI2018,2019,2020,2021
5. ACCV2018,2020
6. WACV2019,2020,2021
7. AAAI2019,2020,2021
8. ECCV2020
9. NIPS2020
10. ICML2021
11. ICLR2022



Trips and Talks

4. ICME, Hongkong, China, July. 2017
3. ACM MM, Brisbane, Australia, Oct. 2015
2. DICTA, Wollongong, Australia, Nov. 2014
1. GTC ( GPU Technology Conference), invited travel, Beijing, China, Dec. 2011

2. " A Case Study for Deep Learning Based on Caffe", UOW invited talk on Deep Learning Workshop, Nov. 2014
1. "A brief introduction to CUDA", UOW invited talk, Wollongong, Australia, Feb. 2014



Work Experience

4. 2017.10-2018.6: I was employed as a researcher at Motovis Inc, and I was in charge of Fixed-point quantization networks, pixel-level semantic labeling, intelligent headlight control.

3. 2013.07-2013.11: I was employed  as a Software Engineer at Beijing Hanze Technology Co., ltd  and I was in charge of the development of software about video enhancement, including FFMpeg video decoding, video enhancement algorithms, denoising algorithms,  and H.264 coding by CUDA.

2. 2011.05-2011.12: I was employed as a Software Engineer at Beijing Maystar Information Technology Co., ltd , and I was in charge of decrypting the Office documents based on GPU.

1. 2010.07-2011.06: I participated a National High-tech R&D Program (863 Program) project at Institute of Wideband Wireless Communication and 3D Imaging (IWWC&3DI): Multi-view video acquisition and demonstration system (2009AA011507). I was in charge of adaptive definition adjustment and format conversion in 3D video network and implemented the 3D video combination algorithm using paralleled methods based on CUDA.

Datasets
1. UOW Online Action3D Dataset: this dataset consists of action sequences of skeleton videos, the 20 actions are from the original MSR Action3D Dataset. The action videos are recorded by Microsoft Kinect V.2 with average 20fms/s frame rate. There are 20 participants to perform these actions, every participant performs each action according to his/her personal habits.  For each participant, he/she first repeats each action 3--5 times, then performs 20 actions continuously in a random order. These continuous action sequences can be used for online action recognition testing. The repeated action sequences will be used for training. In order to make the dataset can be used for cross dataset test, the 20 participants perform the actions in 4 different environments.Please cite the following papers if you use the dataset:
Chang Tang, Wanqing Li, Pichao Wang, Lizhe Wang, "Online Human Action Recognition Based on Incremental Learning of Weighted Covariance Descriptors", Information Sciences,vol.467,pp.219-237, 2018. [pdf][code]