Jun Wan's Homepage

1. Gesture recognition from RGB-D Data 

In our group, one of the research interests is gesture recogniton from RGB-D data. The goal of this project is to develop the robust algorithms and system for human computer interaction (HCI).

Selective Publications (*corresponding author):

[7] Pichao Wang, Wanqing Li, Jun Wan*, Philio Ogunbona, Xinwang Liu, "Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition", AAAI, pp 7404-7411, 2018 (Oral). [PDF]

[6] Jiali Duan, Jun Wan*, Shuai Zhou, Xiaoyuan Guo, Stan Z Li, "A Unified Framework for Multi-Modal Isolated Gesture Recognition", ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2017 (Accept). [PDF]

[4] Jun Wan, Guodong Guo, Stan Z Li, "Explore efficient local features from RGB-D data for one shot learning gesture recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, no. 8, pp. 1626-1639, 2016. [PDF]

[3] Jun Wan, Vassilis Athitsos, Pat Jangyodsuk, Hugo Jair Escalante, Qiuqi Ruan, and Isabelle Guyon "CSMMI: Class-Specific Maximization of Mutual Information for Action and Gesture Recognition", IEEE Transactions on Image Processing (TIP), vol 23(7), pp.3152-3165, 2014 . [PDF]

[2] Jun Wan, Qiuqi Ruan, and Wei Li, "3D SMoSIFT: Three-dimensional Sparse Motion Scale Invariant Feature Transform for Activity Recognition from RGB-D Videos", Journal of Electronic Imaging, 23(2), 023017, 2014. [PDF]

[1] Jun Wan, Qiuqi Ruan, Shuang Deng and Wei Li "One-shot Learning Gesture Recognition from RGB-D Data Using Bag of Features", Journal of Machine Learning Research (JMLR), pp. 2549-2582, vol 14, 2013. [PDF]

Project Demos


  • Chalearn LAP ConGD Database
  • Chalearn LAP IsoGD Database
  • To use both datasets please cite:

  • Jun Wan, Yibing Zhao, Shuai Zhou, Isabelle Guyon, Sergio Escalera and Stan Z. Li, "ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition", CVPR workshop, 2016. [PDF]

2. Automatic Facial Attribute Analysis

In this project, we focus on automatic facial attribute analysis, such as age estimation, race and gender recognition, facial expression recogniton.

Selective Publications (*corresponding author):

[4] Zichang Tan, Jun Wan*, Zhen Lei, Ruicong Zhi, Guodong Guo, Stan Z. Li, "Efficient Group-n Encoding and Decoding for Facial Age Estimation", IEEE TPAMI, Vol 40, No 11, 2018. [PDF][Project]

[3] Jun Wan*, Zichang Tan, Zhen Lei, Stan Z. Li, "Auxiliary Demographic Information Assisted Age Estimation with Cascaded Structure", IEEE Transactions on Cybernetics, Vol 48, No. 9, pp. 2531-2541, 2018. [PDF]

[2] Yiliang Chen, Zichang Tan, Alex Po Leung, Jun Wan, Jianguo Zhang, "Multi-Region Ensemble Convolutional Neural Networks for High Accuracy Age Estimation", BMVC 2017. [PDF]

[1] Zichang Tan, Shuai Zhou, Jun Wan*, Zhen Lei, Stan Z. Li "Age Estimation Based on A Single Network with Soft Softmax of Aging Modeling", In Proceedings of the 13th Asian Conference on Computer Vision (ACCV2016). Taipei, China, 2016. [PDF]

Project Demos


Jun Wan (万军)

Associate Professor

National Laboratory of Pattern Recognition, CASIA

Room 1402, Intelligent Building

95 Zhongguancun Donglu,

Haidian District,

Beijing 100190, China.


jun.wan at ia.ac.cn

joewan10 at gmail.com