Biography of Xin Jin

Xin Jin (金 鑫)

Ph.D., Associate Professor

金鑫，博士，副教授，研究方向为计算美学、计算机视觉、人工智能安全，北京电子科技学院可视计算与安全实验室（victory-lab）主任，北京通用人工智能研究院（BIGAI）访问学者，中国计算机学会高级会员。

教育经历：2013年毕业于北京航空航天大学，虚拟现实技术与系统国家重点实验室，师从赵沁平院士，获得工学博士学位；2009-2010年，中国莲花山计算机视觉和信息科学研究院访问学生，合作导师：前UCLA教授，现国家战略科学家，北京大学智能学院、北京大学人工智能研究院、清华大学通用人工智能研究院（筹）、北京通用人工智能研究院（BIGAI）院长朱松纯；2018-2019年，清华大学信息科学技术学院院长、中国人工智能学会理事长戴琼海院士团队访问学者，合作导师：刘烨斌副教授。

科学研究：在计算机视觉、图像处理、人工智能、多媒体技术等领域的重要学术期刊与会议（ IEEE Trans-IP、IEEE Trans-MM、ACM Trans-MCCAP、ACM Trans-ITS, ACM Trans-IT、AAAI、ACM MM、CVPR、IJCAI、ECCV、ICME等）发表论文60余篇，获国家发明专利授权25项、计算机软件著作权64项、国际学术会议ROSENET2018/19最佳论文奖、ISAIR2017最佳学生论文奖等；主持或参与国家级科研项目9项，省部级及其他科研项目20余项。2019年到2022年在华为中央媒体技术院、西安电子科技大学、中国传媒大学、对外经贸大学、阿里巴巴集团、VALSE2022、CCIG2022、CNCC2020、PRCV2019做主题为视觉美学度量的学术报告。2016年、2019年先后在央广新媒体、中央电视广播总台做“虚拟现实与增强现实前沿”的学术报告。

科研任职：担任国家自然科学基金函评专家、人工智能顶会AAAI、IJCAI程序委员会委员、多媒体顶会ACM MM 2021 Session Chair；AAAI、CVPR、ICCV、IEEE VR、ISMAR、NIPS、IJCAI、ECCV等顶级会议、IEEE Trans-IP、IEEE Trans-MM、IEEE Trans-ITS、ACM Trans-MCCAP、PR等近20项SCI期刊审稿人；担任国际人工智能机器人协会（ISAIR）常务委员、中国图象图形学学会视觉大数据专委会常务委员、中国电子学会虚拟现实分会副秘书长、中国计算机学会计算机视觉专委会执行委员兼专委简报领域主编、中国自动化学会模式识别与机器智能专委会委员兼简报领域主编、中国人工智能学会模式识别专委会委员、中国电影美术学会虚拟空间专委会委员、全国信标委图形图像分委会计算机视觉工作组委员，参与了全国信标委国家标准《信息技术 计算机视觉 术语》的制定。

成果应用：其核心技术已经或正在应用于某头部手机厂商手机智能拍摄、某部委跨平台扫描图像处理、某部委档案图像智能处理、国家档案局照片档案智能着色与修复、证件照人像图像优化处理、数字娱乐智能换脸换妆换光、儿童绘画智能教育系统、泌尿系统肿瘤医学影像智能分析、皮肤病疗效AI测评、医院药房交付药物视频智能确认、中电科视频大数据盲处理、双信道3D图形验证码系统、中石化石油勘探电镜扫描图像智能分析等。

victory-lab (My Research Group : VIsual CompuTing and infORmation securitY)
victory-lab WeChat（实验室微信公众号）:
Faculty（人员） Graduate（研究生） Publications（论文） Talks（报告）

Department of Cyber Security
Beijing Electronic Science and Technology Institute(Besti)

My Google Scholar Citation Profile
My ArXiv Homepage
My ORCiD:0000-0003-3873-1653
My Researchgate Profile
My Linkedin Public Profile

Looking for collaboration with researchers from all over the world.

Contact

jinxinbesti (at) foxmail.com, jinxin (at) besti.edu.cn
Office: (+86) 010 83635114
Room 413 Teaching Building, NO.7, Fufeng Rd. Fengtai District, Beijing, China, 100070

weixin(wechat) / weibo(sina) / facebook / twitter: jinxinbh
QQ: jinxinbh@qq.com, GTalk: jindatou@gmail.com, Skype: jinxin.lhi

News

  • [6 Jul. 2022] One paper entitled “Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment.” has been accpeted by IEEE Transactions on Intelligent Transportation Systems (TITS), which is a top journal on Intelligent Transportaion.

  • [29 Jun. 2022] One paper entitled “Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning” has been accepted by the Technical Demos and Videos Program Track of ACM Multimedia (MM2022), which is a CCF-A conference.

  • [29 Jun. 2022] One paper entitled “Reproducibility Companion Paper: Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies” has been accepted by the Reproducibility Track of ACM Multimedia (MM2022), which is a CCF-A conference.

  • [31 May 2022] One paper entitled “Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets.” has been accpeted by ACM Transactions on Multimedia Computing Communications and Applications (TOMM), which is a top journal on Multimedia.

  • [2 May 2022] One paper entitled “A Deep Drift-Diffusion Model for Image Aesthetic Score Distribution Prediction” has been accepted by IEEE Workshop on Artificial Intelligence for Art Creation (AIART) of IEEE International Conference on Multimedia and Expo Workshop (ICME), which is a CCF-B conference.

Education

Research Interests

  • Visual Computing

    • Computer Vision, Augmented Reality, Scene Understanding
    • Computational Photography, Computational Aesthetics and Visual Arts
    • Illumination Estimation, Evaluation, Transfer and Synthesis

  • Visual Media Security

    • Visual Media Encryption
    • Privacy Preserving/Private/Blind Computer Vision
    • Visual CAPTCHAs

Ph.D Thesis

Perceiving and Representing Artistic Illumination of Face Images (in Chinese). Xin Jin, Beihang University, June, 2013. [Pdf-HD](58.3MB) [Pdf-LR](3.67MB)

Selected Publications

  1. Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning [new]

    • Xin Jin, Shu Zhao, Le Zhang*, Xin Zhao, Qiang Deng, Chaoen Xiao
    • ACM International Conference on Multimedia (ACM MM), Lisbon, Portugal. 10-14 October, 2022
    • Technical Demos and Videos Program Track
    • CCF-A, Top Conference on Multimedia
    • [pdf](2.11MB) [arXiv](2208.04517) [mp4](96MB)

  2. Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies

    • Xin Jin, Zhonglan Li, Ke Liu, Dongqing Zou*, Xiaodong Li, Xingfan Zhu, Ziyin Zhou, Qilong Sun, Qingyu Liu
    • ACM International Conference on Multimedia (ACM MM), Chengdu, China, 20-24 Oct. 2021.
    • Industrial Track
    • CCF-A, Top Conference on Multimedia
    • [pdf](2.11MB) [arXiv](2108.06515)

  3. Aesthetic Evaluation and Guidance for Mobile Photography

    • Hao Lou, Heng Huang, Chaoen Xiao, Xin Jin* (Corresponding Author)
    • ACM International Conference on Multimedia (ACM MM), Chengdu, China, 20-24 Oct. 2021.
    • Technical Demos and Videos Program Track
    • CCF-A, Top Conference on Multimedia
    • [pdf](5.94MB) [mp4](80.09MB)

  4. Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment

    • Qi Kuang, Xin Jin, Qinping Zhao and Bin Zhou
    • IEEE Transactions on Multimedia (TMM), Vol. 22, No. 10, pp. 2623-2634, Oct. 2020.
    • Top Journal on Multimedia, SCI
    • [pdf](7.81MB) [Data]

  5. Confused Modulo Projection based Somewhat Homomorphic Encryption - Cryptosystem, Library and Applications on Secure Smart Cities

    • Xin Jin, Hongyu Zhang, Xiaodong Li*, et al.
    • IEEE Internet of Things Journal (IOTJ), Published Online: 7 Aug. 2020
    • Top Journal on Internet of Things, SCI
    • [pdf](2.91MB)

  6. Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition

    • Shiming Ge, Kangkai Zhang, Haolin Liu, Yingying Hua, Shengwei Zhao, Xin Jin * (Corresponding Author), Hao Wen
    • AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 7-12 Feb. 2020.
    • CCF-A, Top Conference on Artificial Intelligence
      [pdf](1.72MB)

  7. Aesthetic Attributes Assessment of Images

    • Xin Jin, Le Wu, Geng Zhao, Xiaodong Li, Xiaokun Zhang, Shiming Ge, Dongqing Zou, Bin Zhou and Xinghui Zhou.
    • ACM International Conference on Multimedia (ACM MM), Nice, France, 21-25 Oct. 2019.
    • CCF-A, Top Conference on Multimedia
    • [pdf-HD](31.1MB) [pdf-LR](1.11MB) [arXiv](1907.04983) [Data] [Code]

  8. Defending Against Adversarial Examples via Soft Decision Trees Embedding

    • Yingying Hua, Shiming Ge, Xindi Gao, Xin Jin and Dan Zeng.
    • ACM International Conference on Multimedia (ACM MM), Nice, France, 21-25 Oct. 2019.
    • CCF-A, Top Conference on Multimedia
      [pdf](2.47MB)

  9. Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence

    • Xin Jin, Le Wu, Xiaodong Li, Siyu Chen, Siwei Peng, Jingying Chi, Shiming Ge, Chenggen Song, Geng Zhao
    • AAAI Conference on Artificial Intelligence (AAAI), New Orleans, Louisiana, USA. 2-7 Feb. pp.77-84, 2018.
    • CCF-A, Top Conference on Artificial Intelligence
    • [pdf](0.987MB) [arXiv](1708.07089) [Official Online] [Bibtex] [Code]

  10. Learning Templates for Artistic Portrait Lighting Analysis

    • Xiaowu Chen, Xin Jin, Hongyu Wu, Qinping Zhao
    • IEEE Transactions on Image Processing (TIP), Vol. 24, No. 2, pp. 608-618, Feb. 2015
    • CCF-A, Top Journal on Image Processing, SCI
    • [pdf](8.9MB) [mp4](3.06MB) [Project] [Bibtex]

  11. Geodesic Propagation for Semantic Labeling

    • Qing Li, Xiaowu Chen, Yafei Song, Xin Jin, and Qinping Zhao
    • IEEE Transactions on Image Processing (TIP), Vol. 23, No.11, pp. 4812-4825, Nov. 2014
    • CCF-A, Top Journal on Image Processing, SCI
    • [pdf](4.7MB) [Project] [Bibtex]

  12. Face Illumination Manipulation using a Single Reference Image by Adaptive Layer Decomposition

    • Xiaowu Chen *, Hongyu Wu, Xin Jin * (Corresponding Author) and Qinping Zhao
    • IEEE Transactions on Image Processing (TIP), Vol. 2, No. 11, pp. 4249 - 4259, Nov. 2013
    • CCF-A, Top Journal on Image Processing, SCI
    • [pdf](38.7MB) [mp4](20.3M) [Project] [Bibtex]

  13. Face Illumination Transfer through Edge-preserving Filters

    • Xiaowu Chen, Mengmeng Chen, Xin Jin * (Corresponding Author) and Qinping Zhao
    • Computer Vision and Pattern Recognition (CVPR), Colorado Springs, June 20-25, pp.281-287, 2011
    • CCF-A, Top Conference on Computer Vision and Pattern Recognition
    • [pdf](5.03MB) [avi](3.46MB) [Project] [Bibtex]

  14. Artistic Illumination Transfer for Portraits

    • Xiaowu Chen, Xin Jin * (Corresponding Author), Qinping Zhao * and Hongyu Wu
    • Eurographics Symposium on Rendering (EGSR). Paris, France, June 27-29, 2012
    • Computer Graphics Forum (CGF), Vol. 31, NO. 4, pp.1425-1434, 2012
    • CCF-B, SCIE
    • [pdf](43.3MB) avi(30.8MB) [att.](6MB) zip(0.8MB) [Project] [Bibtex]

  15. Supervised Geodesic Propagation for Semantic Label Transfer

    • Xiaowu Chen, Qing Li, Yafei Song, Xin Jin and Qinping Zhao
    • European Conference on Computer Vision (ECCV), Firenze, Italy, October 7-13, pp.553-565 2012.
    • CCF-B
    • [pdf](0.8MB) [mp4](10.5M) [Project] [Bibtex]

  16. Learning Artistic Lighting Template from Portrait Photographs

    • Xin Jin, Mingtian Zhao, Xiaowu Chen, Qinping Zhao, and Song-Chun Zhu
    • European Conference on Computer Vision (ECCV), Heraklion, Crete, Greece, September 5-11, pp.101-114, 2010
    • CCF-B
    • [pdf](1.66MB) [Project] [Bibtex]

  17. Efficient Privacy Preserving Viola-Jones Type Object Detection via Random Base Image Representation

    • Xin Jin, Peng Yuan, Xiaodong Li, Chenggen Song, Shiming Ge, Geng Zhao, Yingya Chen.
    • IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, China, 10-14 July, 2017
    • CCF-B
    • [pdf](0.7MB) [arXiv](1702.08318) [Project] [Bibtex]

  18. 3D Textured Model Encryption via 3D Lu Chaotic Mapping

    • Xin Jin, Shuyun Zhu, Chaoen Xiao, Hongbo Sun, Xiaodong Li, Geng Zhao, Shiming Ge
    • Science China Information Sciences (SCIS), Vol. 60, No. 12, pp.122107:1-9, December 2017.
    • CCF-B, SCIE
    • [pdf](3.17MB) [Published Online] [Data] [Project] [Bibtex]

  19. Single Reference Image based Scene Relighting via Material Guided Filtering

    • Xin Jin, Yannan Li, Ningning Liu, Xiaodong Li,Xianggang Jiang, Chaoen Xiao, Shiming Ge
    • Optics and Laser Technology (JOLT), Vol. 110, pp.7-12, February 2019.
    • JCR-2
    • [Project] Published Online [Bibtex]

  20. Scene Relighting using a Single Reference Image through Material Constrained Layer Decomposition

  21. Lighting Virtual Objects in a Single Image via Coarse Scene Understanding

    • Xiaowu Chen, Xin Jin * (Corresponding Author) and Ke Wang
    • Science China Information Sciences (SCIS). Vol. 57, NO. 9, pp.1-14, 2014
    • CCF-B, SCIE
    • [pdf](13.2MB) [Project] [Bibtex]

  22. Single Image based Illumination Estimation for Lighting Virtual Object in Real Scene

    • Xiaowu Chen, Ke Wang and Xin Jin * (Corresponding Author)
    • International CAD/Graphics Conference. Jinan, China, September 15-17, pp.450-455, 2011
    • [pdf](4.34MB) [avi](15.5MB) [Project] [Bibtex]

  23. Predicting Aesthetic Radar Map using a Hierarchical Multi-task Network

    • Xin Jin, Le Wu, Xinghui Zhou, Geng Zhao, Xiaokun Zhang, Xiaodong Li and Shiming Ge
    • The 1st Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Guangzhou, China, 23-26, November, pp. 41-50, 2018.
    • [pdf](1.5MB) [Bibtex]

  24. ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation

    • Xin Jin, Le Wu, Xiaodong Li, Xiaokun Zhang, Jingying Chi, Siwei Peng, Shiming Ge, Geng Zhao, Shuying Li
    • IET Computer Vision (IET-CVI). Vol. 13, No. 2, pp. 206-212, March 2019.
    • CCF-C
    • [pdf](4.39MB) [arXiv](1610.02256-v3) [Project] [Code] Conference short version: WCSP2016

  25. Deep Image Aesthetics Classification using Inception Modules and Fine-tuning Connected Layer

    • Xin Jin, Jingying Chi, Siwei Peng, Yulu Tian, Chaochen Ye and Xiaodong Li
    • The 8th International Conference on Wireless Communications and Signal Processing (WCSP), Yangzhou, China, 13-15 October, 2016
    • [pdf](5.94MB) [oral presentation](19.1MB) arXiv(1610.02256) [Project] [Code] [Bibtex]

  26. Object Image Relighting through Patch Match Warping and Color Transfer

    • Xin Jin, Yulu Tian, Chaochen Ye, Jingying Chi, Xiaodong Li*, Geng Zhao
    • The 16th International Conference on Virtual Reality and Visualization (ICVRV), Hangzhou, China, 23-25 September, pp.235-241, 2016
    • [pdf](1.47MB) [oral presentation](4.45MB) [Project] [Bibtex]

  27. Color Image Encryption in Non-RGB Color Spaces

    • Xin Jin, Sui Yin, Ningning Liu, Xiaodong Li, Geng Zhao, Shiming Ge
    • Multimedia Tools and Applications (MTAP), Vol. 77, No. 12, pp 15851-15873, June 2018.
    • CCF-C, SCIE
    • [pdf](20.4MB) [Bibtex]

  28. Color Image Encryption in YCbCr Space

    • Xin Jin, Sui Yin, Xiaodong Li, Geng Zhao, Zhaohui Tian, Nan Sun, Shuyun Zhu
    • The 8th International Conference on Wireless Communications and Signal Processing (WCSP), Yangzhou, China, 13-15 October, 2016
    • [pdf](1.83MB) [oral presentation](2.28MB) [Project] [Bibtex]

  29. Color Image Encryption in CIE L*a*b* Space

    • Xin Jin, Yingya Chen, Shiming Ge, et al.
    • The 6th International Conference on Applications and Techniques for Information Security (ATIS), Beijing, China, 4-6 November, pp.74-84, 2015
    • [pdf](6.62MB) [oral presentation](15.2MB) [Project] [Bibtex]

  30. Chaos-Based Image Encryption Scheme Combining DNA Coding and Entropy

    • Ping Zhen, Geng Zhao, Lequan Min and Xin Jin * (Corresponding Author)
    • Multimedia Tools and Applications (MTAP), Vol. 75, No. 11, pp.6303-6319, June 2016
    • CCF-C, SCIE
    • [pdf](2.06MB) [Project] [Bibtex]

  31. 3D Point Cloud Encryption through Chaotic Mapping

    • Xin Jin, Zhaoxing Wu, Chenggen Song, Chunwei Zhang, Xiaodong Li*
    • The Pacific-Rim Conference on Multimedia (PCM), Xi'an China, 15-16 September, 2016
    • CCF-C
    • [pdf](1.47MB) [poster](1.21MB) [Project] [Bibtex]

  32. PPViBe: Privacy Preserving Background Extractor via Secret Sharing in Multiple Cloud Servers

    • Xin Jin, Yaming Wu, Xiaodong Li, Yuzhen Li, Geng Zhao, Kui Guo
    • The 8th International Conference on Wireless Communications and Signal Processing (WCSP), Yangzhou, China, 13-15 October, 2016
    • [pdf](1.24MB) [oral presentation](2.58MB) [Project] [Bibtex]

  33. Private Video Foreground Extraction through Chaotic Mapping based Encryption in the Cloud

    • Xin Jin, Kui Guo, Chenggen Song, Xiaodong Li, Geng Zhao, et al.
    • The 22nd International Conference On Multimedia Modelling (MMM), 4-6 January, 2016 In Miami, USA
    • CCF-C
    • [pdf](4.14MB) [poster](5.37MB) [NDSS2016 Poster] [Project] [Bibtex]

  34. Privacy Preserving Face Identification in the Cloud through Sparse Representation

    • Xin Jin, Yan Liu, Xiaodong Li, Geng Zhao, et al.
    • The 10th Chinese Conference on Biometric Recognition (CCBR), Tianjin, China, 13-15 November, pp.160-167, 2015
    • pdf(694KB) [poster](19.2MB) [NDSS2016 Poster] [Project] [Bibtex]

  35. Cooperatively Resolving Occlusion between Real and Virtual in Multiple Video Sequences

    • Xin Jin, Xiaowu Chen, Bin Zhou, Hongchang Lin
    • ChinaGrid Annual Conference. Dalian, China, August 22-23, pp. 234-240, 2011
    • [pdf](1.03MB) [Project] [Bibtex]

Posters and Workshop Papers

  1. Privacy Preserving Face Retrieval in the Cloud for Mobile Users

    • Xin Jin, Shiming Ge, Chenggen Song
    • Abuse Preventive Data Mining (APDM2017, IJCAI Workshop), 19-25 August, 2017 Melbourne, Australia
    • CCF-A, Top conference on Artificial Intelligence
    • pdf(1.09MB) arXiv(1708.02872) oral presentation(2.97MB)

  2. PPViBe: Privacy Preserving Background Extractor via Secret Sharing in Multiple Cloud Servers

    • Xin Jin, Yaming Wu, Xiaodong Li, Yuzhen Li, Geng Zhao, Kui Guo
    • The Network and Distributed System Security Symposium Poster (NDSS Poster), 26 February – 1 March 2017, In San Diego, California, USA
    • pdf NDSS2017 Official Version

  3. Private Moving Object Detection through Chaotic Mapping based Encryption in the Cloud

    • Xin Jin, Kui Guo, Chenggen Song, Xiaodong Li, Geng Zhao, et al.
    • The Network and Distributed System Security Symposium Poster (NDSS Poster), 21-24 February 2016, In San Diego, California, USA
    • pdf NDSS2016 Official Version

  4. Sparse Representation based Privacy Preserving Face Identification in the Cloud

    • Xin Jin, Yan Liu, Xiaodong Li, Geng Zhao, et al.
    • The Network and Distributed System Security Symposium Poster (NDSS Poster), 21-24 February 2016, In San Diego, California, USA
    • pdf NDSS2016 Official Version

Professional Membership

  • Member of the standing committee of the CSIG Technical Committee of Vision Big Data (CSIG-BVD), Oct. 2020-

  • CCF Senior Member, Sep. 2020-

  • Member of the CSIG Technical Committee of Vision Big Data (CSIG-BVD), Nov. 2018-

  • Member of the CAAI Technical Committee of Pattern Recognition (CAAI-PR), Nov. 2018-

  • Member of Artificial Intelligence Branch of CIITA (CIITA-AI) , July 2018-

  • BJAAI member Beijing Association for Artificial Intelligence, May 2017-

  • Council member of ISAIR: International Society for Artificial Intelligence and Robotics, Apr. 2018-

  • IEEE CS member: IEEE Computer Society, Jan. 2018-

  • Member of the CAA Technical Committee of Pattern Recognition and Machine Intelligence (CAA-PRMI), Nov. 2017-

  • CSIG member: China Society of Image and Graphics, Nov. 2017-

  • CAA member: Chinese Association of Automation, Oct. 2017-

  • Member of the CCF Technical Committee of Computer Vision (CCF-CV), Oct. 2017-

  • CAAI member: Chinese Association for Artificial Intelligence, Apr. 2017-

  • Deputy Secretary General of Virtual/Augmented Reality Branch of CIE (CIE-VRAR), Dec. 2016-

  • CIE member: Chinese Institute of Electronics Nov. 2016-

  • VOOC (VALSE Online Organization Committee) for Vision And Learning Seminar (VALSE), Feb. 2016-

  • Reviewer for National Natural Science Foundation of China, 2015-

  • CCF member: China Computer Federation, Jan. 2014-

  • CCF student member: China Computer Federation, Dec. 2012-Dec.2013

Journal Services

Conference Services

Experiences

  • Jan. 2019~Present, Associate Professor

    • Beijing Electronic Science and Technology Institute

  • Oct. 2013~Dec. 2018, Assistant Professor & Co-Founder of Victory Group

    • VICTORY Group of Besti (VIsual CompuTing and infORmation securitY)
    • Key Laboratory of Information Security, BESTI

  • Nov. 2009~Jun. 2013, Team Leader

    • Lighting and Segmentation Team (3 PhD & 5 graduate students)
    • ARTS Group at SKVRLAB, Beihang University

  • Mar. 2009~Nov. 2009, Assistant Researcher

    • Lotus Hill Institute for Computer Vision and Information Science (LHI)
    • Team of Computational Visual Arts
    • Supervised by Prof. Song-Chun Zhu (UCLA)

  • Sep. 2006~Mar. 2009, Deputy Team Leader

    • Augmented Reality Team (2 PhD & 3 graduate & 3 undergraduate students)
    • SKVRLAB, Beihang University

Invited Talks

  • Aesthetic Assessment of Images and Videos
    -Huawei
    -Aug. 03 2021, Dongguan, China

  • Aesthetic Assessment of Images and Videos
    -GIT Xidian University
    -Apr. 14 2021, Online, China

  • Aesthetic Assessment of Images and Videos
    -CUC
    -Feb. 28 2021, Beijing, China

  • Aesthetic Assessment of Images and Videos
    -UIBE
    -Feb. 28 2021, Beijing, China

  • Aesthetic Assessment of Images and Videos
    -Alibaba
    -Nov. 05 2020, Beijing, China

  • Aesthetic Assessment of Images and Videos
    -CNCC 2020
    -Oct. 22 2020, Hangzhou, China

  • Visual Aesthetics of Robots
    -PRCV 2019
    -Nov. 09 2019, Xi'an, China

  • Frontiers of Virtual Reality and Augmented Reality
    -CCTV
    -Apr. 24 2019, Beijing, China

  • Deep Learning for Crypto Analysis and Design
    -State Key Lab. of Cryptology
    -Jun. 26, 2018, Beijing, China

  • Introduction to Deep Learning and Image Recognition
    -Navinfo
    -Sep. 23 2016, Beijing, China

  • Introduction to Virtual Reality and Augmented Reality
    -CNR
    -May 23, 2016, Beijing, China

  • Learning Templates for Artistic Portrait Lighting Analysis
    -CCBR Youth
    -Nov. 11 2015, Tianjin, China

  • Artistic Illumination Assessment & Manipulation for Portraits
    -Valse Webinar 2015-31
    -Oct. 11 2015
    -Slides(8.51MB)
    -video(iqiyi online)

  • Secure Computing Visual Media
    -State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Science
    -Oct. 11 2014, Xijiao Hotel, Beijing

Current Projects & Funds

  • [In Charge] Jan. 2021~Dec. 2024 NSFC

    • Towards Explainable Computational Model of Visual Aesthetic Appreciation

  • [In Charge] Apr. 2019~Apr. 2021 SKLVR Funds

    • Intelligent Aesthetics in Virtual Reality

  • [Co-In Charge] Jul. 2018~Jul. 2020 SKLC Funds

    • AI for Crypto Design

  • [In Charge] Jan. 2018~Dec. 2019 BKLFS Funds

    • Food Grading via Learning from Image Bigdata

  • [In Charge] Jun. 2018~Jul. 2019 CETC Funds

    • Blind Computing of Government Video Bigdata

  • [Participating] Jan. 2018~Dec. 2020 NSFC

    • The Standard of Chaotic Cipher

Past Projects & Funds

  • [In Charge] May 2018~Oct. 2019 Central Univ. Funds

    • Multi-type Deep Neural Networks for Cryptanalysis

  • [In Charge] May. 2015~May. 2018 SAAC

    • Big Data Driven for Automatic Repair and Annotation of Digital Photo Achieves

  • [Co-In Charge] Apr. 2017~Apr. 2018 Besti Funds

    • Computer Science and Technology

  • [In Charge] Jan. 2015~Dec. 2017 NSFC

    • Content based Image Illumination Template Learning and Aesthetic Quality Assessment

  • [Participating] Jan. 2017~Dec. 2018 NSFC

    • High Dimensional Chaotic Sequence Cipher and its Application in Video Hardware Encryption

  • [In Charge] May. 2016~May. 2018 SKLVR Funds

    • Crowd-sourcing Driven Aesthetic Quality Assessment

  • [In Charge] Jul. 2016~Jul. 2017 Central Univ. Funds

    • Visual Media Encryption in the Cloud

  • [In Charge] Mar. 2014~Mar. 2016 Central Univ. Funds

    • Privacy Preserving Secure Image Processing in the Cloud

  • [In Charge] Oct. 2009~Sep 2016 CAAC-ITRB Funds

    • Deep Learning based Analysis of Coward Activity in the Air Port

  • [Participated] Jan. 2010 ~ Jun. 2013 NSFC Key Project

    • Analysis and Representation of Large-scale Light Field Data

  • [Participated] Mar. 2011 ~ Jun. 2013 **SF

    • Illumination Synthesis and Composition in Aerial images under Varying Illumination

  • [Participated] Aug. 2009 ~ May 2011 863 Program

    • Video-based Virtual Scene Generating System

  • [Participated] Jan. 2009 ~ Dec. 2011 NSFC

    • Realism Assessment of Mixed Reality Scene

  • [Participated] Aug. 2006 ~ Dec. 2008 863 Program

    • Collaborative Augmented Reality

Products

  1. ARDraw: Augmented Reality powered Painter for Children Education [new]

    -Android version-Baidu Mobile[Jun. 10 2018]
    -iOS version-App. Store[Jun. 10 2018]
    -Video Demo(5MB)

  2. Makeup Transfer: One key transfer beautiful makeup you wanted to your own face!

    -iOS version-App. Store[Jan. 8, 2017]

Honors and Awards

  • Outstanding Scientific Research Award, 1st Prize, Besti, 2021

  • Outstanding Scientific Research Award, 1st Prize, Besti, 2020

  • Outstanding Scientific Research Award, 1st Prize, Besti, 2019

  • Outstanding Scientific Research Award, 1st Prize, Besti, 2018

  • Outstanding Scientific Research Award, 1st Prize, Besti, 2017

  • Outstanding Teaching Award, 3rd Prize, Besti, 2017

  • Outstanding Research Papers Award of Graduate Student, Beihang University, 2013

  • Outstanding Achievement Award of Higher School Scientific Research, Technological Invention Award, 1st Prize.
    Rank 9/Student Rank 4. No. 2012-119. Project: Video/Image Driven Virtual Scene Synthesis

  • National Graduate Scholarship, China, 2012 (3/315 Ph.D. Students in SCSE, Beihang University, $4,821)

  • Top 10 Research Papers (Conference) Award of Graduate Student, Beihang University, 2012

  • Outstanding Research Papers Award of Graduate Student, Beihang University, 2011

  • 29th ACM International Collegiate Programming Contest (ICPC), Asia-Beijing Regional, Final, 2004

  • Second Prize, 2th Math Modeling Contest, BUCT, 2003

  • Renmin Scholarship, multiple times, BUCT, 2002~2006

Previous Graduate Students

  1. Xinghui Zhou, Aesthetic Image QA based on Deep Learning. June 2020, Master, Ph.D. Candidate, UCTC, China

  2. Haoyang Yu, Blind Video Processing Method Based on Modular Component Homomorphism. June 2020, Master, Ph.D. Candidate, BUPT, China

  3. Rui Han, 3D Reconstruction based Facial Illumination Analysis and Re-rendering. June 2020, Master, XX Office

  4. Xinxin Li, Illumination Estimation based on Deep Learning. June 2020, Master, Zhongxing, Xi'an

  5. Mingxue Yu, Semantic guided HD Image Generation. June 2020, Master, Weichai, Weifang

  6. Mengyuan Li, Face and Finger Vein Score Layer Fusion Based on Sequential Decision. June 2020, Master, XX Office

  7. Le Wu, Aesthetic Image Captioning based on Deep Learning. June 2019, Master, XX Office

  8. Xing Sun, Sun Orientation Estimation and Illumination Retrival based on Deep Learning. June 2019, Master, Xingtang Communication, Beijing

  9. Yannan Li, Facial Illumination Transfer based on Deep Nerual Networks. June 2019, Master, The People's Bank Of China, Tianjin

  10. Qing Han, Secure Face Recognition in the Cloud. June 2019, Master, Qunar, Beijing

  11. Zhaohui Tian, Deep Learning based CAPTCHA Attack and 3D CAPTCHA. June 2019, Master, JD.com, Beijing

  12. Shuyun Zhu, 3D Model Encryption via Chaos. June 2018, Master, Navinfo, Beijing

  13. Nan Sun, Aesthetic Attributes Assessment of Images. June 2018, Master, XX Office

  14. Sui Yin, Non RGB Color Image Encryption. June 2018, Master, XX Office

  15. Jingying Chi, Deep Image Aesthetic Assessment. June 2017, Master, Xiaomi, Beijing

  16. Yulu Tian, Virtual Image Relighting. June 2017, Master, XX Office

  17. Peng Yuan, Private Image Convolution. June 2017, Master, XX Office

  18. Yaming Wu, Abnormal Detection in School Surveillance Video. June 2017, Master, Fiberhome, Xi'an

  19. Chaochen Ye, Deep Illumination Estimation and Intrinsic Image Decomposition. June 2017, Master, XX Office

  20. Kui Guo, Private Moving Object Extraction for Video Surveillance in the Cloud. June 2016, Master, XX Office

  21. Yingya Chen, Efficient Private Object Detection in the Cloud. June 2016, Master, XX Office

  22. Yan Liu, Privacy Preserving Face Identification in the Cloud. March 2016, Master, Bank of China, Xi’an

  23. Yuzhen Li, Spread Spectrum Communication System via Chaotic Sequence. March 2016, Master, State Grid, Shanghai

  24. Sishui Ye, Image Aesthetics using Deep Leaning. March 2016, Master, 58, Shanghai

  25. Ping Zhen, Public Key Cryptography based on Chebyshev Polynomials. June, 2016, Ph.D. State Grid, Beijing

  26. Guangzheng Wei, Chaotic Mapping and DNA Encoding based Image Encryption. June, 2015, Master, XX Office

Previous Undergraduate Students

  1. Renhan Xu, Augmented Reality Magic Draw. June 2018. XX Office

  2. Qiliang Jiang, Portrait Shooting Assissant via Deep Learning. June 2018. XX Office

  3. Xinyu Xu, Encrypted Cloud Storage Tools. June 2018. XX Office

  4. Zhanhong Lin, Smart Photo Album. June 2017. XX Office

  5. Lu Cha, AR Draw on Mobile Phone. June 2017. XX Office

  6. Zijian Jia, 3D CAPTCHAR on Mobile Phone. June 2017. XX Office

  7. Zhaoxing Wu, 3D Point Cloud Encryption. June 2017. XX Office

  8. Xingyu Su, UAV Control for Image Processing in Mobile Phone. June 2017. XX Office

  9. Chunwei Zhang, AR CAPTCHAR in Mobile Phone. June 2017. XX Office

  10. Jiaxing Chi, Suveillance video Summarization and Synopsis. June 2016. XX Office

  11. Jun Wu, Crowdsourcing based Online Challenge Plantform on Photography. June 2016. XX Office

  12. Yuan Yao, Kinect based Real-time 3D Reconstruction. June, 2016. XX Office

  13. Yi Zheng, Robot Photographer. June, 2016. XX Office

  14. Ziyi Wang, Color Image Enctyption. June, 2015. XX Office

  15. Hongbin Wu, Data Driven Image Relighting. June, 2015. XX Office

Past News

  • [11 Aug. 2021] One paper entitled “Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies” has been accepted by ACM Multimedia (MM2021) Industrial Track, which is a CCF-A conference.

  • [29 Jul. 2021] One paper entitled “Aesthetic Dashboard: Rich Aesthetic Evaluation and Guidance for Mobile Photography” has been accepted by ACM Multimedia (MM2021) Technical Demos and Videos Program Track, which is a CCF-A conference.

  • [16 Oct. 2020] I have been selected as a member of the standing committee of CSIG-BVD.

  • [25 Sep. 2020] I have been certified as CCF Senior Membership.

  • [18 Sep. 2020] I have been supported by NSFC 2020 on Explainable Computational Model of Visual Aesthetic Appreciation.

  • [04 Sep. 2020] I have been selected as an associate editor for Elsevier Cognitive Robotics (a new journal).

  • [05 Aug. 2020] One paper entitled “Confused Modulo Projection based Somewhat Homomorphic Encryption - Cryptosystem, Library and Applications on Secure Smart Cities.” has been accpeted by IEEE Internet of Things Journal (IOTJ), which is a top journal on IOT according to CAS-JCR (IF = 9.936).

  • [13 Dec. 2019] Our dataset on Aesthetic Attribute Captions is opened online: DPC-Cations, which was proposed by our ACM Multimedia 2019 paper.

  • [06 Dec. 2019] One paper entitled “Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment” has been accpeted by IEEE Transactions on Multimedia (TMM), which is a top journal on multimedia.

  • [11 Nov. 2019] One paper entitled “Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition” has been accepted by AAAI Conference on Artificial Intelligence (AAAI2020), which is a CCF-A conference.

  • [23 Oct. 2019] One paper entitled “Double-Blinded Finder: A Two-Side Secure Children Face Recognition System” has been accepted by Wireless Networks (WINET), which is a CCF-C SCIE journal.

  • [19 Sep. 2019] One paper entitled “Efficient Blind Face Recognition in the Cloud” has been accepted by Multimedia Tools and Applications (MTAP), which is a CCF-C SCIE journal.

  • [01 Jul. 2019] One paper entitled “Aesthetic Attributes Assessment of Images” has been accepted by ACM Multimedia (MM2019), which is a CCF-A conference.

  • [01 Jul. 2019] One paper entitled “Defending Against Adversarial Examples via Soft Decision Tree Embedding” has been accepted by ACM Multimedia (MM2019), which is a CCF-A conference.

  • [01 Jun. 2019] One paper entitled “Image Aesthetic Quality Assessment: A Survey” was reprinted by Xinhua Digest (No.18, 2018).

  • [02 Feb. 2019] One paper entitled “Secure Face Retrieval for Group Mobile Users” has been accepted by Soft Computing (SOCO), which is a CCF-C SCIE journal.

  • [06 Dec. 2018] One paper entitled “Two open-source projects for image aesthetic quality assessment” has been accepted by SCIENCE CHINA Information Sciences (SCIS), which is a CCF-B SCIE journal.

  • [20 Sep. 2018] One paper entitled “Recent advances on blind vision” has been published in Science & Technology Review (in Chinese)

  • [09 Aug. 2018] One paper entitled “A Secure and Efficient Face-Recognition Scheme based on Deep Neural Network and Homomorphic Encryption” has been accepted as an oral paper by International Conference on Virtual Reality and Visualization (ICVRV), Qingdao, China, 22-24, October, 2018.

  • [08 Aug. 2018] One paper entitled “Sun Orientation Estimation from a Single Image using Short-cuts in DCNN” has been accepted by Optics and Laser Technology (JOLT), which is a JCR-2 SCIE journal.

  • [02 Aug. 2018] One paper entitled “Predicting Aesthetic Radar Map using a Hierarchical Multi-task Network” has been accepted by The 1st Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Guangzhou, China, 23-26, November, 2018.

  • [02 Aug. 2018] One co-authored paper entitled “Weighted Linear Multiple Kernel Learning for Saliency Detection” has won the Best Paper Award of ROSENET2018.

  • [20 July 2018] One paper entitled “IDEA: A New Dataset for Image Aesthetic Scoring” has been accepted by Multimedia Tools and Applications (MTAP), which is a CCF-C SCIE journal.

  • [26 May 2018] One paper entitled “Image Aesthetic Quality Assessment: A Survey” has been published in Science & Technology Review (in Chinese).

  • [22 May 2018] One paper entitled “ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation” has been accepted by IET Computer Vision (IET-CVI), which is a CCF-C SCIE journal.

  • [12 May 2018] Three papers have been accepted by EAI International Conference on Robotic Sensor Networks (ROSENET2018), Kitakyushu, Japan, 25–26, August, 2018

  • [11 Apr. 2018] I have been selected as a council member for International Society for Artificial Intelligence and Robotics (ISAIR)

  • [16 Mar. 2018] Three papers have been accepted by International Symposium on Artificial Intelligence and Robotics (ISAIR2018), Nanjing, China, 17-19, November, 2018

  • [18 Dec. 2017] The deadline of ISAIR2018 Special Session on Computational Aesthetics and Visual Arts Analysis [CFP] has been extended to March 1. To ensure that your accepted papers are recommonded to SCI journals, please submit your papers before this date. This is the confirmed deadline. There will be no extension in the furture. Looking forward to see you in Nanjing in November 2018.

  • [02 Dec. 2017] One paper entitled “Image Editing by Object-Aware Optimal Boundary Searching and Mixed-Domain Composition” has been accepted by Computational Visual Media (CVMJ).

  • [25 Nov. 2017] I have been selected as the CAA Technical Committee of Pattern Recognition and Machine Intelligence Member (CAA-PRMI).

  • [09 Nov. 2017] Call for papers: ISAIR2018 Sepcial Session on Computational Aesthetics and Visual Arts Analysis. [CFP]. All of the accepted papers will be recommended to special issues in sustainability-related SCI indexed journals. I am the chair of this session. Welcome to submit your papers.

  • [08 Nov. 2017] One paper entitled “Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence” has been accepted by AAAI Conference on Artificial Intelligence (AAAI2018), which is a CCF-A conference.

  • [08 Nov. 2017] One paper entitled “Single Reference Image based Scene Relighting via Material Guided Filtering” has been accepted by Optics and Laser Technology (JOLT), which is a JCR-2 SCIE journal.

  • [03 Nov. 2017] I join the China Society of Image and Graphics (CSIG).

  • [24 Oct. 2017] I join the Chinese Association of Automation (CAA).

  • [21 Oct. 2017] One paper entitled “3D Textured Model Encryption via 3D Lu Chaotic Mapping” has been accepted by Science China Information Sciences (SCIS), which is a CCF-B SCIE journal.

  • [11 Oct. 2017] I have been selected as the CCF Technical Committee of Computer Vision Member (CCF-CV) in CCCV2017, Tianjin, China.

  • [04 Oct. 2017] 中文主页上线：http://www.escience.cn/people/jinxin, 还在完善中，欢迎访问！

  • [28 Aug. 2017] One paper entitled “Color Image Encryption in Non-RGB Color Spaces” has been accepted by Multimedia Tools and Applications (MTAP), which is a CCF-C SCIE journal.

  • [20 Aug. 2017] One workshop paper entitled “Privacy Preserving Face Retrieval in the Cloud for Mobile Users” was presented at IJCAI 2017 workshop (Abuse Preventive Data Mining (APDM2017, IJCAI Workshop), Melbourne, Australia)

  • [17 Aug. 2017] One NSFC project entitled “The Standard of Chaotic Cipher” I particpate has been approved.

  • [17 Aug. 2017] New record of the aesthetic classification accuracy on the AVA dataset by our group: 82.66%.

  • [24 Jul. 2017] One paper has been selected as ISAIR2017 Best Student Paper Award.

  • [16 Jul. 2017] One paper has been nominated for ISAIR2017 Best Paper Awards.

  • [09 Jul. 2017] One paper has been accepted by International Symposium on Artificial Intelligence and Robotics (ISAIR), Kitakyushu, Japan, 25-26, November, 2017

  • [15 Jun. 2017] One paper has been accepted by Abuse Preventive Data Mining (APDM, IJCAI Workshop), Melbourne, Australia 19-25 August, 2017

  • [08 Jun. 2017] One App named “AR Draw” has been available on Android Market.

  • [25 Mar. 2017] Two papers have been accepted by IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, China, 10-14 July, 2017 (CCF-B).

  • [02 Feb. 2017] Two posters have been accepted by the Network and Distributed System Security Symposium (NDSS Poster), San Diego, California, USA 26 February – 1 March, 2017

  • [23 Jan. 2017] The second baby of mine was born in Beijing.

  • [08 Jan. 2017] One App named “Makeup Transfer” has been available on App Store.

Update : August 21 2021 by Xin Jin