SHORT INSTRUCTION

Yanli Ji, Ph.D, is currently a Professor (PhD supervisor) in the University of Electronic Science and Technology of China (UESTC). She obtained her Ph.D degree from Department of Advanced Information Technology, Kyushu University, Japan at Sep. 2012. She was a visiting researcher at the University of Tokyo from Nov. 2018 to Jan. 2020. Her research interests focus on Audio-visual Multimodal Information Understanding and Emotion Cognition Focusing on Human.

She has published papers in TIP, TMM, TKDE, TCSVT, PR, Signal processing, CVPR, ACM MM, etc. She has obtained ‘28th Australasian Database Conference Best Paper Award’ and ‘20th China Virtual Reality Conference Best Paper Nomination Award’. More than 20 patents have been released. She has directed and undertaken more than 10 research projects from natural science foundation of China (NSFC), and horizontal cooperation projects from company. She is active in professional services, and participants the organization of several conferences, i.e. ACCV 2022, ACMMM 2021, ACMMM Asia 2021, ICME, VALSE 2015-2022 and ACM SIGAI CHINA symposium in TURC, 2017-2019. She is the CCF Senior Member, Executive Member and Vice Executive Secretary of Youth Working Committee of CSIG, Vice Chairman of VALSE SAC.

电子科技大学教授，博士生导师，博士毕业于日本九州大学，东京大学客员研究员。研究方向：围绕人的音视觉多模态信息理解、情感认知。发表TIP，TMM，TKDE，TCSVT，PR，Signal processing, CVPR，ACM MM等SCI期刊论文及高水平国际会议论文，申请近三十项发明专利。获得28th Australasian Database Conference国际会议Best Paper Award，第二十届中国虚拟现实大会最佳论文提名奖。主持国家自然科学基金青年项目和面上项目，主持和参与十多项国家级、省部级、知名企业横向项目。多次参与承办国际会议和国内学术峰会，学术兼职包括国际会议ACCV2022 Industrial Chair，ACMMM2021 Financial chair，ACMMM Asia 2021 Workshop chair，ICME Registration Chair，国内学术峰会VALSE 2015-2022，以及ACM SIGAI CHINA symposium in TURC, 2017-2019 Local Chair等。中国计算机学会高级会员(CCF Senior Member)，中国图象图形学会青年工作委员会执行委员、副秘书长，VALSE委员会SAC副主席。

 

RESEARCH INTERESTS

·  Human Action Recognition and Skeleton Extraction in Natural Scenes;

·  Audio-visual Multimodal Information Understanding and Emotion Cognition Focusing on Human;

 

PROFESIONAL EXPERIENCE

Professor	Aug. 2022 - Now
University of Electronic Science and Technology of China, Chengdu, China.
Associate professor	Aug. 2016 - July 2022
University of Electronic Science and Technology of China, Chengdu, China.
Lecturer	Jan. 2013 - July 2016
University of Electronic Science and Technology of China, Chengdu, China.
Visit Researcher	Nov. 2015 - Jan. 2016
Lab of Image/Media Understanding, Department of Advanced information Technology, Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan.
Visiting Researcher	Nov. 2018 - Jan. 2020
The Tokyo University, Tokyo, Japan.

 

EDUCATION

Kyushu University, Fukuoka, Japan	Oct. 2009 – Sep. 2012
Ph.D, Department of Advanced Information Technology Thesis: Recognition of Human Actions using Visual Local Features Advisor: Prof. Rin-ichiro Taniguchi. Advisor Panel: Prof. Ryo Kurazume, Associate Prof. Hajime Nagahara.
Chongqing University, Chongqing, China	Sep. 2005 – July 2008
Master, Image Processing, College of Communication Engineering Thesis: Image Compression based on Optical Wavelet Transform. Advisor: Prof. Fengchun Tian.
Chongqing University, Chongqing, China	Sep. 2001 – July 2005
Bachelor, College of Communication Engineering.

 

PROJECTS

2021.10-2024.10 Basic Research of Shenzhen Science and Technology Innovation Commission, Research on Intelligent Human Behavior Understanding and human-robot Interaction based on Contextual Emotion. Principal Investigator. (面上项目， JCYJ20210324132203007)

2019-2022 Science and Technology Department of Sichuan Province, Research on few-shot self-learning technology for multi-source social perception data, Co-investigator. (重大专项)

2018-2022 Out-of-Province Industry-University-Research (IUR) Project, Efficient and scalable data cleaning, redundancy and other data fusion methods, Co-investigator.

2018-2020 Out-of-Province Industry-University-Research (IUR) Project, Research on Theory and Technology of Unified Representation Model for Multi-source Heterogeneous Data, Co-investigator.

2017.01-2020.12 Natural Science Funding of China (NSFC), Multi-mode Learning on Moving-view Human Activity Recognition and Human-robot Interactions for Service Robot Application. Principal Investigator. (面上项目，No. 61673088)

2016.08-2018.07 Fundamental Research Funds for the Central Universities, Study on visual based emotion cognition and interaction for social robots, Principal Investigator.

2016.01-2019.12 Natural Science Funding of China (NSFC), 4D Human-Robot Interaction Event Understanding for Social Robots. Co-investigator. (面上项目，No. 61573084)

2016.01-2019.12 Natural Science Funding of China (NSFC), Research on Key Technologies of Collaborative Visual Semantic Understanding and Social Media Analysis Co-investigator. (面上项目，No. 61572108)

2015.08-2018.08 Chengdu Technology Transfer (Group) Co. Ltd (CTG), Cooperative development protocol for interactive social service robots and their series of core technologies. Co-investigator.

2015.08-2016.07 Ricoh Software Research Center (SRCB), Video Analysis using Deep Learning. Co-investigator.

2014.01-2016.12 Natural Science Funding of China for Young Scientists (NSFC), The Spatio-Temporal Co-Occurrence Model Based Human Interaction Recognition in Group Activity Understanding. Principal Investigator. (青年基金，No. 61305043)

2014.01-2015.12 Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry, STCO-Model based Human Group Interaction Understanding. Principal Investigator. (留学归国基金)

2014.01-2016.01 Fundamental Research Funds for the Central Universities, Semantic understanding of multi-person interaction using spatio-temporal Context features, Principal Investigator.

2012.10-2013.06 Huawei Technologies Co. Ltd, Research on freedom head motion based eye gazing system. Principal Investigator.

2012.09-2013.09 Huawei Technologies Co. Ltd, Hand gesture used HCI in conference system. Co-investigator.

 

TEACHING

·  Digital Signal Processing, H0700330.02, Semester 2, 2013-2014.

·  Digital Signal Processing, H0700330.03, Semester 2, 2014-2015.

·  Pattern Recognition, 0718420.01, Semester 2, 2014-2015.

·  Digital Image Processing, H0720630.02, Semester 2, 2015-2016.

·  Signal and System, Semester 1, 2016-2017.

·  Machin Learning, Semester 2, 2019-2020.

 

Professional Services

·  Registration Chair, ICME (IEEE International Conference on Multimedia & Expo), Chengdu, China, July, 2014.

·  Conference secretary, Vision And Learning Seminar (VALSE), Chengdu, China, May, 2015. Workshop Chair of VALSE 2018, Dalian, April, 2018.

·  Program Chair, ACM SIGAI CHINA symposium in ACM Turing 50th Celebration Conference, 2017; Program Chair, 2018.

·  Reviewer for TNNLS, Neurocomputing,TIP, Pattern Recognition, Journal of Human Computer Interaction, JVCIR, Signal processing, CVPR, ICCV, ECCV, etc.

·  IEEE, ACM member, CCF, CAAI committee member. Deputy secretary-general of SIGAI China.

·  VALSE Online Program Committee Member, Deputy secretary-general of VALSE, http://www.valseonline.org/.

 

SELECTED PUBLICATIONS

1.  Y Ji, S Ma, Self-supervised Fine-grained Cycle Separation Network (FSCN) for Visual Audio Separation, TMM, Aug. 2022. (中科院JCR二区)

 

2.  L Gao, Y Ji, Global-local Cross-view Fisher Discrimination for View Invariant Action Recognition, ACM MM, Oct. 2022. (CCF A, 通讯作者)

 

3.  G Wang, X Xu, F Shen, H Lu, Y Ji, H T Shen. Cross-modal Dynamic Networks for Video Moment Retrieval with Text Query, TMM, 2022. (中科院JCR二区)

 

4.  Y Ji, Y Hu, Y Yang, HT Shen. Region Attention Enhanced Unsupervised Cross-Domain Facial Emotion Recognition, IEEE Transactions on Knowledge and Data Engineering, 2021. (中科院JCR一区)

 

5.  X Zhu, H Li, HT Shen, Z Zhang, Y Ji, Y Fan. Fusing functional connectivity with network nodal information for sparse network pattern learning of functional brain networks, Information Fusion, Vol. 75, 131-139, 2021. (中科院JCR一区)

 

6.  S Ma, Y Ji, X Xu, X Zhu. Vision-guided Music Source Separation via a Fine-grained Cycle-Separation Network, ACMMM, 4202-4210, 2021. (CCF A, 通讯作者)

 

7.  L Gao, Y Ji, X Xu, X Zhu, HT Shen. View-invariant Human Action Recognition via View Transformation Network, TMM , 2021. (中科院JCR二区, 通讯作者)

 

8.  K Gedamu, Y Ji, Y Yang, L Gao, HT Shen. Arbitrary-view human action recognition via novel-view action generation, Pattern Recognition, Vol. 118, 108043, 2021. (中科院JCR二区, 通讯作者)

 

9.  Y Zhu, X Xu, Y Ji, F Shen, HT Shen, H Lu. Graph Convolutional Hourglass Networks for Skeleton-Based Action Recognition, ICME, 1-6, 2021. (CCF B)

 

10.  Y Ji, Y Yang, HT Shen, T Harada. View-invariant action recognition via Unsupervised AttentioN Transfer (UANT), Pattern Recognition, Vol. 113, 2021. (中科院JCR二区)

 

11.  J Wei, Y Yang, X Xu, Y Ji, X Zhu, HT Shen. Graph-based variational auto-encoder for generalized zero-shot learning, ACM MM Asia, 1-7, 2021. (CCF C)

 

12.  Y Fu, M Zhang, X Xu, Z Cao, C Ma, Y Ji, K Zuo, H Lu. Partial Feature Selection and Alignment for Multi-Source Domain Adaptation, CVPR, 2021. (CCF A)

 

13.  M Zhang, Y Yang, X Chen, Y Ji, X Xu, J Li, HT Shen. Multi-stage aggregated transformer network for temporal language localization in videos, CVPR, 2021. (CCF A)

 

14.  L Peng, Y Yang, X Zhang, Y Ji, H Lu, HT Shen. Answer Again: Improving VQA with Cascaded-Answering Model, IEEE Transactions on Knowledge and Data Engineering, 2020. (中科院JCR一区)

 

15.  Y Ji, Y Yang, F Shen, HT Shen, WS Zheng. Arbitrary-view Human Action Recognition: A Varying-view RGB-D Action Dataset, TCSVT, Vol. 31 (1), 289-300, 2020. (中科院JCR二区)

 

16.  J Wei, X Xu, Y Yang, Y Ji, Z Wang, HT Shen. Universal Weighting Metric Learning for Cross-modal Matching, CVPR, 2020. (CCF A)

 

17.  Y Li, A Bozic, T Zhang, Y Ji, T Harada, M Nießner. Learning to Optimize Non-Rigid Tracking CVPR, 2020. (CCF A)

 

18.  Y Ji, Y Zhan, Y Yang, X Xu, F Shen, H T Shen. A Knowledge Map Guided Coarse-to-fine Action Recognition, TIP, 2019. (中科院JCR一区)

 

19.  Y Ji, Y Zhan, Y Yang, X Xu, F Shen, HT Shen. A Context Knowledge Map Guided Coarse-to-Fine Action Recognition, TIP, Vol. 29, 2742-2752, 2019. (中科院JCR一区)

 

20.  Y Ji, F Xu, Y Yang, N Xie, HT Shen, T Harada. Attention Transfer (ANT) Network for View-invariant Action Recognition, ACMMM, 574-582, 2019. (CCF A)

 

21.  Y Ji, Y Yang, F Shen, HT Shen, X Li. A Survey of Human Action Analysis in HRI Applications, TCSVT, Vol. 30 (7), 2114-2128, 2020. (中科院JCR二区)

 

22.  Y Ji, Y Hu, Y Yang, F Shen, HT Shen. Cross-domain facial expression recognition via an intra-category common feature and inter-category Distinction feature fusion network, Neurocomputing, Vol. 333, 231-239, 2019. (中科院JCR二区)

 

23.  X Xu, L He, H Lu, L Gao, Y Ji. Deep adversarial metric learning for cross-modal retrieval, World Wide Web, Vol. 22 (2), 657-672, 2019. (中科院JCR三区)

 

24.  L Peng, Y Yang, Y Bin, N Xie, F Shen, Y Ji, X Xu. Word-to-region attention network for visual question answering, Multimedia Tools and Applications, Vol. 78 (3), 3843-3858, 2019. (中科院JCR三区)

 

25.  Y Ji, F Xu, Y Yang, F Shen, HT Shen, WS Zheng. A Large-scale RGB-D Database for Arbitrary-view Human Action Recognition, ACMMM, 1510-1518, 2018. (CCF A)

 

26.  X Xu, H Wu, Y Yang, F Shen, N Xie, Y Ji. Semantic binary coding for visual recognition via joint concept-attribute modelling, Multimedia Tools and Applications, Vol. 77 (17), 22185-22198, 2018. (中科院JCR三区)

 

27.  C Liu, H Lu, H Wei, X Xu, Y Ji. Domain separation network for cross-modal retrieval, ICIMCS, 1-5, 2018.

 

28.  Y Yang, J Zhou, J Ai, Y Bin, A Hanjalic, HT Shen, Y Ji. Video Captioning by Adversarial LSTM, TIP, Vol. 27 (11), 5600-5611, 2018. (中科院JCR一区)

 

29.  M Zhang, Y Yang, H Zhang, Y Ji, HT Shen, TS Chua. More is better: Precise and detailed image captioning using online positive recall and missing concepts mining, TIP, Vol. 28 (1), 32-44, 2018. (中科院JCR一区)

 

30.  Y Ji, H Li, Y Yang, S Li. Hierarchical topology based hand pose estimation from a single depth image, Multimedia Tools and Applications, Vol. 77 (9), 10553-10568, 2018. (中科院JCR三区)

 

31.  M Zhang, Y Yang, Y Ji, N Xie, F Shen. Recurrent attention network using spatial-temporal relations for action recognition, Signal Processing, Vol. 145, 137-145, 2018. (中科院JCR二区)

 

32.  C Liu, X Xu, Y Yang, H Lu, F Shen, Y Ji. Domain Invariant Subspace Learning for Cross-Modal Retrieval, MMM, 94-105, 2018. (CCF C)

 

33.  Y Ji, Y Yang, X Xu, HT Shen. One-shot Learning based Pattern Transition Map for Action Early Recognition, Signal Processing, Vol. 143, 364-370, 2018. (中科院JCR二区)

 

34.  H Wu, J Shao, X Xu, Y Ji, F Shen, HT Shen. Recognition and Detection of Two-Person Interactive Actions Using Automatically Selected Skeleton Features, IEEE Transactions on Human-Machine Systems, Vol. 48 (3), 304-310, 2018. (中科院JCR二区)

 

35.  Y Ji, Y Hu, Y Yang, F Shen, H Shen. Cross-database Facial Expression Recognition via an Intra-category Common Feature and Inter-category Distinguishing Feature Fusion Network, Neurocomputing, 2018.

 

36.  H Cheng, Y Liu, W Fu, Y Ji. Gazing point dependent eye gaze estimation, Pattern Recognition, Vol. 71, 36-44, 2017. (中科院JCR二区)

 

37.  M Zhang, Y Yang, H Zhang, Y Ji, N Xie. Deep Semantic Indexing Using Convolutional Localization Network with Region-Based Visual Attention for Image Database, Australasian Database Conference, 261-272, 2017. (Best paper Award)

 

38.  Y Ji, J Li, H Cheng, X Xu, J Song. Multi-cue Information Fusion for Two-layer Activity Recognition. ACCV workshop HIS, 2016.

 

39. Y Ji, H Cheng, Y Zheng, H Li. Learning contrastive feature distribution model for interaction recognition. Journal of Visual Communication and Image Representation, 33, pp. 340–349, 2015.

 

40. Y Ji, G Ye, H Cheng. Interactive body part contrast mining for human interaction recognition, Proc. in ICME Workshop Hot3D, 2014.

 

41. Y Ji, A Shimada, H Nagahara and R Taniguchi.　Contribution estimation of participants for human interaction recognition. IEEJ Transactions on Electrical and Electronic Engineering. 8(3), 2013.

 

42. Y Ji, Y Ko, A Shimada, H Nagahara and R Taniguchi. Cooking Gesture Recognition using Local Feature and Depth Image. Proc. of ACMMM in workshop CEA 2012.

 

43. Y Ji, A Shimada, H Nagahara and R Taniguchi. SOM-based Human Action Recognition Using Local Feature Descriptor CHOG3D. Research Reports on Information Science and Electrical Engineering of Kyushu University, 17(1), 2012.

 

44. B Tong, W Jia, Y Ji, E Suzuki: Linear Semi-Supervised Dimensionality Reduction with Pairwise Constraint for Multiple Subclasses. IEICE TRANSACTIONS on Information and Systems, E95-D(3), pp.812-820, 2012.

 

45. Y Ji, A Shimada, H Nagahara and R Taniguchi. Human-human interaction recognition by estimating the action contribution of participants. Proceedings of the 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision, Kawasaki, Japan. 2012, 2.

 

46. Y Ji, A Shimada, H Nagahara and R Taniguchi. A Compact Descriptor CHOG3D and its Application in Human Action Recognition. IEEJ Transactions on Electrical and Electronic Engineering. 8(1), 2013.

 

47. Y Ji, A Shimada, R Taniguchi. A Compact 3D Descriptor in ROI for Human Action Recognition, IEEE TENCON 2010.　(WIE Best Paper Award).

 

SELECTED PATENT

1.  A Visual-assisted Cross-modal Audio Signal Separation Method (视觉辅助跨模态音频信号分离方法)，202011537001.1.

2.  A Controllable Expression Generation Method Combined with Style Transfer (结合风格迁移的可控表情生成方法)，202011618332.8.

3.  An Arbitrary-view Action Recognition Method (任意视角动作识别方法)，202011541269.2.

4.  An Automatic Attendance Checking Method Based on Visual Head Detection (一种基于视觉头部检测的自动考勤方法)，201711161391.5.

5.  An Intelligent Supervised Method for Attention Based on Gaze Estimation (一种基于视线估计的注意力智能监督方法)，201710546644.4.

6.  A Method for Estimating Hand Poses on Depth Images using Correction Processing (一种基于深度信息和校正方式的手部姿态估计方法), 201610321710.3.

7.  A 3D Eye Gazing Estimation Method and Its Application in a Long-short Distance HRI (一种基于3D视线估计的远近距离人机交互系统与方法), 201610133124.6.

8.  A Method for Global Hand Pose Detection in Depth Data (一种基于深度数据的手部全局姿态检测方法), 201610093720.6.

9.  A 3D Gesture Pose Estimation Method and System Based on Deep Data (一种基于深度数据的三维手势姿态估计方法及系统)，201510670919.6.

10.  A 3D Eye Gazing Estimation Method using Eye Landmarks (基于眼部关键点检测的3D视线方向估计方法)，201611018884.9.

11.  STDW based continue Hand Gesture trajectory Recognition (一种基于STDW的连续字符手势轨迹识别方法)，201610688950.7.

12.  Multi-posed Fingertip Tracking and Its Application in Natural HRI (用于自然人机交互的多姿态指尖跟踪方法), 201610070474.2.

13.  Target Model based Continue Hand trajectory Segmentation Method and System (基于目标模型信息的连续手势轨迹分割方法及系统)，CN201610442838.5.

14.  An Image Sequence Oriented Spatial Motion Reconstruction Method for Articulated Joints (一种面向图像序列的铰接关节点空间运动重构方法), 201610154349.X.

15.  A Human Computer Interaction Method Based on Eye Gaze Tracking (一种基于眼动跟踪的人机交互方法), 201310684342.5.

 

DATABASE

1.  CR-UESTC Interaction Database, ftp://121.48.158.70:8100/;

2.  UESTC RGB-D Varying-view action database: https://github.com/HRI-UESTC/CFM-HRI-RGB-D-action-database;

If you want to use the database, feel free to contact us, please.
Back to top.