基本信息

万军  男  副研究员 硕士研究生导师  

中国科学院自动化研究所

模式识别国家重点实验室
电子邮件: jun.wan@ia.ac.cn
通信地址: 北京市海淀区中关村东路95号
邮政编码: 100190

更多信息(个人主页):http://www.cbsr.ia.ac.cn/users/jwan/


国家重点研发计划“战略性科技创新合作”重点专项首席,中国科学院对外合作重点项目负责人,基金委国际(地区)合作项目负责人,IEEE Senior Member, Chalearn理事会成员,研究方向为智能视频分析与理解、智能交互。在国际主流期刊和会议上发表论文70余篇、专(编)著 3 本,ESI高被引论文一篇,Google Scholar 2300余次(H-index 26),其中一作/通讯作者发表在人工智能顶级期刊IEEE TPAMI(3篇)、机器学习顶级期刊JMLR、计算机视觉顶级期刊IJCV(2篇)、图像处理顶级期刊IEEE TIP(5篇)、自动控制顶级期刊IEEE TCYB(3篇) 、多媒体顶级期刊IEEE TMM,以及计算机视觉和人工智能顶级会议CVPR、AAAI、IJCAI 上。受IEEE TPAMI主编、多伦多大学Sven Dickinson教授邀请以第一作者撰写首部多模态人脸防伪专著。担任IEEE TPAMI和IEEE TBIOM客座编辑、SCI期刊IET Biometrics 副主编和ICME 2021/2022 领域主席,AAAI 2021 Senior PC, 在ICPR 2016 ICCV 2017CVPR 2019、CVPR 2020、ICCV 2021国际顶级会议举办组织研讨会和比赛,累计吸引超过1200支国内外队伍参赛,获得国内外广泛关注。曾获得第十三届北京青年优秀科技论文一等奖,北京地区2020 年广受关注学术成果优秀论文、国内外竞赛冠亚军5项等。主持国家重点研发专项,中科院对外合作重点项目、国家自然科学基金项目(3 项,含国际合作项目1项)、澳门科技大学 -澳门科技发展基金项目子课题(2 项)和多项企业项目(如华为、百度、京东、马上消费金融)等项目10余项。

研究领域

模式识别、计算机视觉、机器学习、深度学习


欢迎具有计算机、自动化、电子信息、数学专业的考生联系报考, 可与我邮件联系 jun.wan@ia.ac.cn


在中科院自动化所和李子青研究员联合培养的博士生谭资昌同学获得中国科学院院长奖、中国科学院大学三好学生、唐立新奖学金,自动化所攀登一等奖学金、北京市优秀毕业生、国科大优秀毕业生

招生信息

招生专业
081104-模式识别与智能系统
招生方向

计算机视觉、智能视频分析与理解、视频结构化分析、智能交互技术(手势/手语)



教育背景

2008-09--2015-01   北京交通大学   博士研究生/工学博士
2004-09--2008-06   中国地质大学(北京)   本科/工学学士

工作经历

   
工作简历
2018-11~现在, 中国科学院自动化研究所模式识别国家重点实验室, 副研究员
2015-01~2018-10,中国科学院自动化研究所模式识别国家重点实验室, 助理研究员
社会兼职
2020-12-01-今,IEEE Transactions on Biometrics, Behavior, and Identity Science, 客座编辑
2020-02-01-2023-12-31,IET Biometrics, 副主编
2019-07-30-今,国际电子与电气工程协会会员, IEEE Senior Member
2018-10-31-2020-06-30,百度研究院, 百度IDL学术顾问
2018-08-01-2020-08-30,IEEE Transactions on Pattern Analysis and Machine Intelligence, 客座编辑
2018-08-01-2019-01-31,京东 AI 研究院-京东葡萄树访问学者计划, 访问研究员
2018-01-28-今,Chalearn, 理事会成员
2015-12-29-2019-07-28,国际电子与电气工程协会会员, IEEE Member

专利与奖励

   
奖励信息
(1) HEART-MET国际手势识别竞赛, 二等奖, 其他, 2021
(2) CAIP国际年龄估计竞赛, 一等奖, 其他, 2021
(3) 北京地区广受关注学术成果(物联网领域)优秀论文, , 其他, 2020
(4) "地面哨兵"挑战赛(国防科技创新特区专家组举办), 二等奖, 其他, 2020
(5) 京东葡萄树学者计划突出贡献奖, 其他, 2019
(6) 华为全球开发者大赛优秀合作伙伴奖, , 其他, 2018
(7) FG国际微表情竞赛, 一等奖, 其他, 2017
(8) 中国电子学会优秀博士论文提名奖, , 其他, 2016
(9) 第十三届北京青年优秀科技论文, 一等奖, 省级, 2016
(10) 北京交通大学优秀博士论文奖, , 其他, 2015
专利成果
( 1 ) 基于卷积神经网络的人脸图像年龄估计算法, 发明, 2019, 第 1 作者, 专利号: ZL201610857697.3
( 2 ) 基于多任务学习的卷积神经网络的人脸属性分析方法, 发明, 2019, 第 1 作者, 专利号: ZL201610856231.1
( 3 ) 基于 RGB-D 数据构成的少量训练样本的手势识别方法, 发明, 2016, 第 1 作者, 专利号: ZL201310522370.7
( 4 ) 人脸图像生成方法及装置, 发明, 2020, 第 2 作者, 专利号: ZL201711157541.5
( 5 ) 基于人脸多区域的人脸属性识别系统, 发明, 2021, 第 1 作者, 专利号: ZL201910210915.8
( 6 ) 基于跨模态转化辅助的人脸防伪检测方法、系统及装置, 发明, 2021, 第 1 作者, 专利号: ZL202010802184.9

出版信息

截止2022年3月,第一或通讯作者发表在IEEE/ACM Trans.CCF A类国际期刊/会议论文26篇,包含TPAMI长文3篇,JMLR长文1篇,IJCV长文2篇,TIP长文4篇

发表论文
[1] Yang, Yang, Tan, Zichang, Tiwari, Prayag, Pandey, Hari Mohan, Wan, Jun, Lei, Zhen, Guo, Guodong, Li, Stan Z. Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition. INTERNATIONAL JOURNAL OF COMPUTER VISION[J]. 2021, 129(10): 2731-2744, http://dx.doi.org/10.1007/s11263-021-01499-z.
[2] Wang, Zhan, Wang, Lizhi, Wan, Jun, Huang, Hua. Shared Low-Rank Correlation Embedding for Multiple Feature Fusion. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2021, 23: 1855-1867, [3] Liu, Ajian, Li, Xuan, Wan, Jun, Liang, Yanyan, Escalera, Sergio, Escalante, Hugo Jair, Madadi, Meysam, Jin, Yi, Wu, Zhuoyuan, Yu, Xiaogang, Tan, Zichang, Yuan, Qi, Yang, Ruikun, Zhou, Benjia, Guo, Guodong, Li, Stan Z. Cross-ethnicity face anti-spoofing recognition challenge: A review. IET BIOMETRICSnull. 2021, 10(1): 24-43, http://dx.doi.org/10.1049/bme2.12002.
[4] Yu, Zitong, Zhou, Benjia, Wan, Jun, Wang, Pichao, Chen, Haoyu, Liu, Xin, Li, Stan Z, Zhao, Guoying. Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2021, 30: 5626-5640, [5] Liu, Ajian, Tan, Zichang, Wan, Jun, Liang, Yanyan, Lei, Zhen, Guo, Guodong, Li, Stan Z. Face Anti-Spoofing via Adversarial Cross-Modality Translation. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY[J]. 2021, 16: 2759-2772, https://www.webofscience.com/wos/woscc/full-record/WOS:000639651900006.
[6] Zhou, Benjia, Li, Yunan, Wan, Jun. Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition. 2021, http://arxiv.org/abs/2102.05348.
[7] 万军. Special Issue on Face Presentation Attack Detection. IEEE Transactions on Biometrics, Behavior, and Identity Science. 2021, [8] Moeslund, Thomas B, Escalera, Sergio, Anbarjafari, Gholamreza, Nasrollahi, Kamal, Wan, Jun. Statistical Machine Learning for Human Behaviour Analysis. ENTROPYnull. 2020, 22(5): https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7517024/.
[9] Yu, Zitong, Wan, Jun, Qin, Yunxiao, Li, Xiaobai, Li, Stan Z, Zhao, Guoying. NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing. 2020, http://arxiv.org/abs/2011.02062.
[10] Li, Xuan, Wan, Jun, Jin, Yi, Liu, Ajian, Guo, Guodong, Li, Stan Z, IEEE. 3DPC-Net: 3D Point Cloud Network for Face Anti-spoofing. IEEE/IAPR INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB 2020)null. 2020, [11] Escalera, Sergio, Escalante, Hugo Jair, Baro, Xavier, Guyon, Isabelle, Madadi, Meysam, Wan, Jun, Ayache, Stephane, Gucluturk, Yagmur, Guclu, Umut. Guest Editorial: Image and Video Inpainting and Denoising. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCEnull. 2020, 42(5): 1021-1024, https://www.webofscience.com/wos/woscc/full-record/WOS:000523685800001.
[12] Lin, Xuxin, Wan, Jun, Xie, Yiliang, Zhang, Shifeng, Lin, Chi, Liang, Yanyan, Guo, Guodong, Li, Stan Z. Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis. IEEE TRANSACTIONS ON CYBERNETICS[J]. 2020, 50(3): 1292-1305, http://dx.doi.org/10.1109/TCYB.2019.2917049.
[13] Liu Ajian, Li Xuan, Wan Jun, Escalera Sergio, Escalante Hugo Jair, Madadi Meysam, Jin Yi, Wu Zhuoyuan, Yu Xiaogang, Tan Zichang, Yuan Qi, Yang Ruikun, Zhou Benjia, Guo Guodong, Li Stan Z. Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review. 2020, http://arxiv.org/abs/2004.10998.
[14] Zhang, Shifeng, Xie, Yiliang, Wan, Jun, Xia, Hansheng, Li, Stan Z, Guo, Guodong. WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2020, 22(2): 380-393, http://dx.doi.org/10.1109/TMM.2019.2929005.
[15] Li Ajian, Tan Zichang, Li Xuan, Wan Jun, Escalera Sergio, Guo Guodong, Li Stan Z. CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing. 2020, http://arxiv.org/abs/2003.05136.
[16] Li, Yunan, Wan, Jun, Miao, Qiguang, Escalera, Sergio, Fang, Huijuan, Chen, Huizhou, Qi, Xiangda, Guo, Guodong. CR-Net: A Deep Classification-Regression Network for Multimodal Apparent Personality Analysis. INTERNATIONAL JOURNAL OF COMPUTER VISION[J]. 2020, 128(12): 2763-2780, http://dx.doi.org/10.1007/s11263-020-01309-y.
[17] Zhang, Shifeng, Wang, Xiaobo, Liu, Ajian, Zhao, Chenxu, Wan, Jun, Escalera, Sergio, Shi, Hailin, Wang, Zezheng, Li, Stan Z, IEEE Comp Soc. A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)null. 2019, 919-928, [18] Tan, Zichang, Yang, Yang, Wan, Jun, Hang, Hanyuan, Guo, Guodong, Li, Stan Z. Attention-Based Pedestrian Attribute Analysis. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 28(12): 6126-6140, http://dx.doi.org/10.1109/TIP.2019.2919199.
[19] Lin, Xuxin, Liang, Yanyan, Wan, Jun, Lin, Chi, Li, Stan Z. Region-Based Context Enhanced Network for Robust Multiple Face Alignment. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2019, 21(12): 3053-3067, http://dx.doi.org/10.1109/TMM.2019.2916455.
[20] Fu, Yunfang, Ruan, Qiuqi, Luo, Ziyan, Jin, Yi, An, Gaoyun, Wan, Jun. FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion. SIGNAL PROCESSING[J]. 2019, 161: 74-88, http://ir.ia.ac.cn/handle/173211/24597.
[21] Zhang Shifeng, Liu Ajian, Wan Jun, Liang Yanyan, Guo Guogong, Escalera Sergio, Escalante Hugo Jair, Li Stan Z. CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing. 2019, http://arxiv.org/abs/1908.10654.
[22] 万军. Task-oriented Feature-fused Network with Multi-variate Dataset for Joint Face Analysis. IEEE Transactions on Cybernetics. 2019, [23] 万军. Multi-modal Face Anti-spoo?ng Attack Detection Challenge at CVPR2019. CVPR workshop. 2019, [24] 万军. Deeply-learned Hybrid Representation for Facial Age Estimation. IJCAI. 2019, [25] Zhang Shifeng, Xie Yiliang, Wan Jun, Xia Hansheng, Li Stan Z, Guo Guodong. WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild. 2019, http://arxiv.org/abs/1909.12118.
[26] Wan Jun, Lin Chi, Wen Longyin, Li Yunan, Miao Qiguang, Escalera Sergio, Anbarjafari Gholamreza, Guyon Isabelle, Guo Guodong, Li Stan Z. ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition. 2019, http://arxiv.org/abs/1907.12193.
[27] Wan, Jun, Escalera, Sergio, Perales, Francisco J, Kittler, Josef. Articulated motion and deformable objects. PATTERN RECOGNITION[J]. 2018, 79: 55-64, http://dx.doi.org/10.1016/j.patcog.2018.01.038.
[28] Wan, Jun, Tan, Zichang, Lei, Zhen, Guo, Guodong, Li, Stan Z. Auxiliary Demographic Information Assisted Age Estimation With Cascaded Structure. IEEE TRANSACTIONS ON CYBERNETICS[J]. 2018, 48(9): 2531-2541, https://www.webofscience.com/wos/woscc/full-record/WOS:000442362100003.
[29] Lin, Chi, Wan, Jun, Liang, Yanyan, Li, Stan Z, IEEE. Large-scale Isolated Gesture Recognition Using a Refined Fused Model based on Masked Res-C3D Network and Skeleton LSTM. PROCEEDINGS 2018 13TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE & GESTURE RECOGNITION (FG 2018)null. 2018, 52-58, [30] Jun Wan, Wanqing Li, Pichao Wang, Xinwang Liu, Philip Ogunbona. Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition. 2018, http://arxiv.org/abs/1801.01080.
[31] Tan, Zichang, Wan, Jun, Lei, Zhen, Zhi, Ruicong, Guo, Guodong, Li, Stan Z. Efficient Group-n Encoding and Decoding for Facial Age Estimation. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2018, 40(11): 2610-2623, http://dx.doi.org/10.1109/TPAMI.2017.2779808.
[32] Guo, Jianzhu, Lei, Zhen, Wan, Jun, Avots, Egils, Hajarolasvadi, Noushin, Knyazev, Boris, Kuharenko, Artem, Silveira Jacques Junior, Julio C, Baro, Xavier, Demirel, Hasan, Escalera, Sergio, Allik, Jueri, Anbarjafari, Gholamreza. Dominant and Complementary Emotion Recognition From Still Images of Faces. IEEE ACCESS[J]. 2018, 6: 26391-26403, https://doaj.org/article/5956debd1d9c462b8348b5e8b865190b.
[33] Fan, YangYu, Liu, Shu, Li, Bo, Guo, Zhe, Samal, Ashok, Wan, Jun, Li, Stan Z. Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2018, 20(8): 2196-2208, http://dx.doi.org/10.1109/TMM.2017.2780762.
[34] Wang, Pichao, Li, Wanqing, Ogunbona, Philip, Wan, Jun, Escalera, Sergio. RGB-D-based human motion recognition with deep learning: A survey. COMPUTER VISION AND IMAGE UNDERSTANDING[J]. 2018, 171: 118-139, http://dx.doi.org/10.1016/j.cviu.2018.04.007.
[35] Wan Lipeng, Wan Jun, Jin Yi, Tan Zichang, Li Stan Z, IEEE. Fine-grained Multi-attribute Adversarial Learning for Face Generation of Age, Gender and Ethnicity. 2018 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB)null. 2018, 98-103, [36] Duan, Jiali, Wan, Jun, Zhou, Shuai, Guo, Xiaoyuan, Li, Stan Z. A Unified Framework for Multi-Modal Isolated Gesture Recognition. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS[J]. 2018, 14(1): https://www.webofscience.com/wos/woscc/full-record/WOS:000433517100007.
[37] Wang, Pichao, Li, Wanqing, Wan, Jun, Ogunbona, Philip, Liu, Xinwang, AAAI. Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2018, 7404-7411, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485488907062.
[38] Escalante, Hugo Jair, Guyon, Isabelle, Athitsos, Vassilis, Jangyodsuk, Pat, Wan, Jun. Principal motion components for one-shot gesture recognition. PATTERN ANALYSIS AND APPLICATIONS[J]. 2017, 20(1): 167-182, https://www.webofscience.com/wos/woscc/full-record/WOS:000393053200012.
[39] Wan Jun, Escalera Sergio, Anbarjafari Gholamreza, Jair Escalante Hugo, Baro Xavier, Guyon Isabelle, Madadi Meysam, Allik Juri, Gorbova Jelena, Lin Chi, Xie Yiliang, IEEE. Results and Analysis of ChaLearn LAP Multi-modal Isolated and Continuous Gesture Recognition, and Real versus Fake Expressed Emotions Challenges. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017)null. 2017, 3189-3197, [40] Wan, Jun, Escalera, Sergio, Anbarjafari, Gholamreza, Jair Escalante, Hugo, Baro, Xavier, Guyon, Isabelle, Madadi, Meysam, Allik, Juri, Gorbova, Jelena, Lin, Chi, Xie, Yiliang, IEEE. Results and Analysis of ChaLearn LAP Multi-modal Isolated and Continuous Gesture Recognition, and Real versus Fake Expressed Emotions Challenges. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017)null. 2017, 3189-3197, [41] Tan, Zichang, Zhou, Shuai, Wan, Jun, Lei, Zhen, Li, Stan Z, Lai, SH, Lepetit, V, Nishino, K, Sato, Y. Age Estimation Based on a Single Network with Soft Softmax of Aging Modeling. COMPUTER VISION - ACCV 2016, PT IIInull. 2017, 10113: 203-216, [42] Jair Escalante, Hugo, PonceLopez, Victor, Wan, Jun, Riegler, Michael A, Chen, Baiyu, Clapes, Albert, Escalera, Sergio, Guyon, Isabelle, Baro, Xavier, Halvorsen, Pal, Muller, Henning, Larson, Martha, IEEE. ChaLearn Joint Contest on Multimedia Challenges Beyond Visual Analysis: An overview. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)null. 2016, 67-73, [43] Liu Ting, Wan Jun, Yu Tingzhao, Lei Zhen, Li Stan Z, Zhou J, You Z, Wang Y, Sun Z, Shan S, Zheng W, Feng J, Zhao Q. Age Estimation Based on Multi-Region Convolutional Neural Network. BIOMETRIC RECOGNITIONnull. 2016, 9967: 186-194, [44] Wan, Jun, Guo, Guodong, Li, Stan Z. Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2016, 38(8): 1626-1639, https://www.webofscience.com/wos/woscc/full-record/WOS:000379926200011.
[45] Shuai Zhou, Stan Z Li, Zhen Lei, Zichang Tan, Jun Wan. Age Estimation Based on a Single Network with Soft Softmax of Aging Modeling. 2016, http://ir.ia.ac.cn/handle/173211/15298.
[46] Jun Wan, Stan Z Li, Zhen Lei, Ting Liu, Tingzhao Yu. Age Estimation based on Multi-Region Convolutional Neural Network. 2016, http://ir.ia.ac.cn/handle/173211/20050.
[47] Stan Z Li, Ting liu, Zhen Lei, Jun Wan. DFDnet: Discriminant Face Descriptor Network for Facial Age Estimation. Springer---Lecture Notes in Computer Sciencesnull. 2015, http://ir.ia.ac.cn/handle/173211/11536.
[48] Li, Wei, Ruan, Qiuqi, Wan, Jun. Dimensionality reduction using graph-embedded probability-based semi-supervised discriminant analysis. NEUROCOMPUTING[J]. 2014, 138: 283-296, http://dx.doi.org/10.1016/j.neucom.2014.02.005.
[49] Wan, Jun, Athitsos, Vassilis, Jangyodsuk, Pat, Jair Escalante, Hugo, Ruan, Qiuqi, Guyon, Isabelle. CSMMI: Class-Specific Maximization of Mutual Information for Action and Gesture Recognition. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2014, 23(7): 3152-3165, https://www.webofscience.com/wos/woscc/full-record/WOS:000337842700012.
[50] Wan, Jun, Ruan, Qiuqi, Li, Wei, An, Gaoyun, Zhao, Ruizhen. 3D SMoSIFT: three-dimensional sparse motion scale invariant feature transform for activity recognition from RGB-D videos. JOURNAL OF ELECTRONIC IMAGING[J]. 2014, 23(2): https://www.webofscience.com/wos/woscc/full-record/WOS:000338984000017.
[51] Li, Wei, Ruan, Qiuqi, Wan, Jun. Graph-preserving shortest feature line segment for dimensionality reduction. NEUROCOMPUTING[J]. 2013, 110: 80-91, http://dx.doi.org/10.1016/j.neucom.2012.11.020.
[52] Li, Wei, Ruan, Qiuqi, Wan, Jun. Fuzzy Nearest Feature Line-based Manifold Embedding for Facial Expression Recognition. JOURNAL OF INFORMATION SCIENCE AND ENGINEERING[J]. 2013, 29(2): 329-346, https://www.webofscience.com/wos/woscc/full-record/WOS:000316242600008.
[53] Wan, Jun, Ruan, Qiuqi, Li, Wei, Deng, Shuang. One-shot Learning Gesture Recognition from RGB-D Data Using Bag of Features. JOURNAL OF MACHINE LEARNING RESEARCH[J]. 2013, 14(1): 2549-2582, https://www.webofscience.com/wos/woscc/full-record/WOS:000327007400003.
[54] Wan, Jun, Ruan, Qiuqi, An, Gaoyun, Li, Wei, Baozong, Y, Qiuqi, R, Xiaofang, T. Hand Tracking and Segmentation via Graph Cuts and Dynamic Model in Sign Language Videos. PROCEEDINGS OF 2012 IEEE 11TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP) VOLS 1-3null. 2012, 1135-1138, 
发表著作
(1) Inpainting and Denoising Challenges, Spring, 2019-06, 第 3 作者
(2) Statistical Machine Learning for Human Behaviour Analysis, MDPI, 2020-07, 第 5 作者
(3) Multi-Modal Face Presentation Attack Detection, Morgan & Claypool Publishers, 2020-08, 第 1 作者

科研活动

1. SCI 期刊 IET Biometrics (影响影子 2.039) 副主编 (Associate Editor),2020.02-2023.12

2. 人工智能顶级期刊 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, 影响因子 17.73) 客座编辑, Special Topic on Image and Video Inpainting and Denoising, 2018-2020.

3. SCI 期刊 Entropy 客座编辑, Special Topic on Statistical Machine Learning for Human Behavior Analysis, 2019.

4. SCI 期刊 Machine Vision and Applications 客座编辑,Special Issue on Human Abnormal Behavioural Analysis,2018-2019.

5. 作为联合负责人,在计算机视觉顶级会议 CVPR 上组织了多媒体取证研讨会,主要是组织人脸防伪竞赛的相关工作 (CVPR 2020 Workshop on Media Forensics), 2020.

6. 作为第一负责人,在计算机视觉顶级会议 CVPR 上组织了人脸防伪竞赛以及研讨会 (CVPR 2019 Workshop on Face Spoofing Workshop and Competition), 2019.

7. 作为第一负责人,在计算机视觉顶级会议 ICCV 上组织了动作、手势和表情识别竞赛和 研讨会 (ICCV 2017 Workshop on Action, Gesture, and Emotion Recognition Workshop and Competitions: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions).

8. 作为共同负责人(排名第二): 在计算机视觉会议 ICPR 上组织了多媒体分析竞赛和研讨会 (ICPR 2016 Workshop on ChaLearn Joint Contest on Multimedia Challenges Beyond Visual Analysis).

9. 计算机视觉/机器学习期刊审稿人: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Journal of Machine Learning Research (JMLR), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Cybernetics (TCYB), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Multimedia (TMM), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), IEEE Transactions on Human-Machine Systems (THMS), IEEE Transactions on Information Forensics and Security (TIFS), IEEE Signal Processing Letters (SPL), IEEE Access, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), ACM Transactions on Intelligent Systems and Technology (TIST), Pattern Recognition (PR), Pattern Recognition Letter(PRL), IET Computer Vision, Neurocomputing,Frontiers of Computer Science (FCS). 

10. 计算机视觉领域顶级/权威大会程序委员和审稿人: AAAI 2022 (Senior Program Committee)FG 2021, CCBR 2021,ACM MM 2021, BMVC 2021, ICCV 2021, ICME 2021 (Area/Session Chair), CVPR2021, AAAI 2021, WACV 2021, BMVC 2020, ECCV 2020, FG 2020, CVPR 2020, AAAI 2020, CVPR 2019, ICCV 2019, BMVC 2019, ICME 2019, BTAS 2019, PRCV 2019, FG 2019, CCBR 2019, CVPR 2018, ECCV 2018, ACCV 2018, BTAS 2018, BigMM 2018.

11. 国际著名非盈利性竞赛组织 Chalearn 理事, 2018-至今.

12. IEEE Member (2016.01-2019.08), IEEE Senior Member (2019.08-至今)

13. CCF Member, 2013-至今

科研项目
( 1 ) 基于视频时空信息建模的人脸结构化分析, 主持, 国家级, 2020-01--2022-12
( 2 ) 人脸、指纹、虹膜及多模态快速识别技术应用研究, 主持, 省级, 2019-11--2020-12
( 3 ) 多元人脸属性协同学习方法研究, 主持, 国家级, 2019-01--2022-12
( 4 ) 基于 RGB-D 数据的个性化手势交互技术研究, 主持, 国家级, 2016-01--2018-12
( 5 ) 人脸防伪关键技术研究, 主持, 省级, 2019-01--2021-12
( 6 ) 多模态人体特征识别算法与系统, 主持, 省级, 2019-06--2022-06
( 7 ) 大规模视频目标的跨时空多维度关联, 参与, 国家级, 2016-07--2019-06
( 8 ) 面向昇腾算子开发的技术合作项目, 主持, 院级, 2020-03--2020-07
( 9 ) 复杂场景自主认知与集群决策关键技术研究, 主持, 部委级, 2021-01--2023-12
( 10 ) 基于华为Atlas800训练服务器训练深度学习模型-NRE合作项目, 主持, 院级, 2020-12--2021-03
( 11 ) RGB人脸静默活体检测算法, 主持, 院级, 2021-05--2022-06
( 12 ) 通用视觉模型关键技术研究, 主持, 国家级, 2021-12--2024-11
( 13 ) 基于物理和数字攻击的视频人像证伪, 主持, 国家级, 2021-12--2024-11

指导学生

   
指导学生

  1. 谭资昌  博士研究生  081104-模式识别与智能系统 (联合培养,博士期间发表一作论文TPAMI 2018, IJCV 2021, TIP (2篇, 2022, 2019), AAAI 2020, IJCAI 2019,ACCV 2016, 2016.01-2021.07;毕业工作去向:百度) 

  2. 刘阿建 博士研究生 计算机科学与技术 (澳科大联培博士生,已发表/接收一作论文IJCAI 2022,TIFS 2022 (2篇), WACV 2021, TBIOM 2020, IET Biometrics 2020, 2018.09-2022.05)

  3. 周本加  博士研究生  人工智能 (澳科大博士生,已发表一作论文CVPR 2022, AAAI 2021, TIP 2021, VRIH2020, 2018.09-至今)

  4. 包增浩  硕士研究生  电子信息 (联合培养,多篇一作论文在投和在审,2020.09-至今) 

  5. 李    俊  硕士研究生  081104-模式识别与智能系统 (已发表一作论文CVPR 2022,2021.09-至今)

  6. 陈志刚  硕士研究生  081104-模式识别与智能系统 (2021.09-至今)

  7. 钮龙宇  硕士研究生  081104-模式识别与智能系统(2021.09-至今)

  8. 方    好  硕士研究生  电子信息 (2021.09-至今)