中文 English

jia

Professor JIA Yunde

 

Beijing Lab of Intelligent Information Technology

School of Computer Science

Beijing Institute of Technology

Beijing100081, PR China

 

Tel: 86-10-6891-4849

Email: jiayunde@bit.edu.cn

http://iitlab.bit.edu.cn/mcislab/

 

JIA Yunde received the B.S., M.S., and Ph.D. degrees from the Beijing Institute of Technology (BIT) in 1983, 1986, and 2000, respectively. He was a visiting scientist with the Robotics Institute, Carnegie Mellon University (CMU), from 1995 to 1997. He is currently a Professor with the School of Computer Science, BIT, and the team head of BIT innovation on vision and media computing. He serves as the director of Beijing Lab of Intelligent Information Technology. His interests include computer vision, vision-based HCI and HRI, and intelligent robotics.

 

Courses

Computational Perception (Graduate students), Fall.

Image Processing and understanding (Undergraduate), Fall.

 

Research topics

l  Computer Vision

l  Machine Learning and Image Understanding

l  Face Recognition Technology

l  Intelligent Human Computer Interaction

l  Embedded Visual Computing

l  Intelligent Robot System

 

Selected International Journal Papers

(2018)

1.       JING Chenchen, DONG Zhen, PEI Mingtao, and JIA Yunde, Heterogeneous Hashing for Face Retrieval across Image and Video Domains, IEEE Transactions on Multimedia (T-MM), 2018.

2.       HOU Jingyi, WU Xinxiao, Yuchao SUN,JIA Yunde, Content-Attention Representation by Factorized Action-Scene Network for Action Recognition, IEEE Transactions on Multimedia (T-MM), 2018.

3.       SONG Hao, WU Xinxiao, ZHU Bin, WU Yuwei, CHEN Mei, and JIA Yunde, Temporal Action Localization in Untrimmed Videos using FP-trees, IEEE Transactions on Multimedia (T-MM), 2018.

4.       SONG Hao, WU Xinxiao, YU Wennan, JIA Yunde, Extracting Key Segments of Videos for Event Detection by Learning from Web Sources, IEEE Transactions on Multimedia (T-MM), 2018.

5.     WANG Yucheng, ZHANG Jian,WU Qiang, LIU Zicheng, ZHANG Zhenyou, and JIA Yunde, Depth Super-Resolution on RGB-D Video Sequences with Large Displacement 3D Motion, IEEE Transactions on Image Processing (T-IP), 2018.

6.     SHENG Weichao, WU Yuwei, YUAN Junsong, TAN Yap Peng, ZHANG Jian, and JIA Yunde, Robust Distracter-Resistive Tracker via Learning A Multi-component Discriminative Dictionary, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT) 28, 2018.

7.       DONG Zhen, JING Chenchen, PEI Mintao, JIA Yunde, Deep CNN based Binary Hash Video Representations for Face Retrieval, Pattern Recognition, 2018.

8.       BU Xinyuan, WU Yuwei, Gao Zhi, JIA Yunde, Deep Convolutional Network with Locality and Sparsity Constraints for Texture Classification Article, Pattern Recognition, 2018.

9.       LIU Cuiwei, Hou Jingyi, WU Xinxiao, and JIA Yunde, A Discriminative Structural Model for Joint Segmentation and Recognition of Human Actions, Multimedia Tools and Applications, 2018.

10.    HOU Jingyi, WU Xinxiao, Jin Chen, LUO Jianbo, and JIA Yunde, Unsupervised Deep Learning of Mid-Level Video Representation for Action Recognition, In Proc. of the AAAI Conference on Artificial Intelligence (AAAI-18), 2018.

11.    YU Lidong, WANG Yucheng, WU Yuwei and JIA Yunde, Deep Stereo Matching with Explicit Cost Aggregation Sub-Architecture, In Proc. of the AAAI Conference on Artificial Intelligence (AAAI-18), 2018.

12.    GAO Zhi, WU Yuwei, and JIA Yunde, Set-to-Set Distance Metric Learning on SPD Manifolds, In Proc. of the First Chinese Conference on Pattern Recognition and Computer Vision (PRCV18), Guangzhou, 2018.

13.    王文冠,沈建冰,贾云得, 视觉注意力检测综述,软件学报,2018.

(2017)

1.       YANG Min, WU Yuwei, JIA Yunde, Hybrid Local/Global Data Association for Robust Online Multi-Object Tracking, IEEE Transactions on Image Processing (T-IP), 26(12): 5667-5679, 2017.

2.       SHEN Weichao, WU Yuwei, and JIA Yunde, A Compact Discriminative Object Representation via Weakly Supervised Learning for Real-time Visual Tracking, IET Computer Vision, IET Computer Vision 11(7): 585-595 , 2017.

3.       WANG Han, WU Xinxiao, JIA Yunde, Heterogeneous domain adaptation for video annotation. IET Computer Vision 11(2): 181-187, 2017.

4.       SONG Hao, WU Xinxiao, LIANG Wei, JIA Yunde, Recognizing key segments of videos for video annotation by learning from web image sets, Multimedia Tools and Applications (MTA), 76(5): 6111-6126, 2017.

5.       YU Changyong and JIA Yunde, Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection, arXiv preprint arXiv: 1707.02692, 2017.

6.       XU Bin and JIA Yunde, Wide-angle image stitching using multi-homography warping, 2017 IEEE International Conference on Image Processing (ICIP2017), Beijing, China, 2017.

(2016)

1.       YANG Jiaolong, LI Hongdong, and JIA Yunde, Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 38(11): 2241-2254, 2016.

2.       LIU Cuiwei, WU Xinxiao, and JIA Yunde, A Hierarchical Video Description for Complex Activity Understanding, International Journal of Computer Vision (IJCV), 118(2): 240-255, 2016.

3.       LIU Cuiwei, WU Xinxiao, and JIA Yunde, Transfer Latent SVM for Joint Recognition and Localization of Actions in Videos, IEEE Trans. on Cybernetics (T-CYB), 46(11), 2596-2608, 2016.

4.       YANG Ming, JIA Yunde, Temporal Dynamic Appearance Modeling for Online Multi-Person Tracking, Computer Vision and Image Understanding 153: 16-28, 2016.

5.       WANG Yucheng, ZHANG Jian, WU Qiang, CHOU Philip, ZHANG Zhengyou, JIA Yunde, Handling Occlusion and Large Displacement through Improved RGB-D Scene Flow Estimation, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 26(7): 1265-1278, 2016.

6.       YANG Ming, WU Yuwei, PEI Mingtao, MA Bo, and JIA Yunde, Online Discriminative Tracking with Active Example Selection, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 26(7): 1279-1292, 2016.

7.       DONG Zhen, LIANG Wei,WU Yuwei, PEI Mingtao and JIA Yunde, Nonnegative Correlation Coding for Image Classification, SCEINCE CHINA Information Science, 59(1): 1-14, 2016.

8.       FENG Yang, WU Xinxiao, JIA Yunde, Multi-Group Multi-Class Domain Adaptation for Event Recognition, IET Computer Vision, 10(1): 60-66, 2016.

9.       DONG Zhen, PEI Mintao, JIA Yunde, Orthonormal Dictionary Learning and its Application to Face Recognition, Image and Vision Computing (IVC), 51: 13-21, 2016.

10.       SHEN Jiajun, XU Bin, PEI Mintao, and JIA Yunde, A low-cost telepresence robotic wheelchair system, In Proc. of IEEE/RSJ Int. Conf. on Robots and Intelligent Systems (IROS), South Korea, 2016.

(2015)

1.       JIA Yunde, XU Bin, SHEN Jiajun, PEI Mintao, DONG Zhen, HOU Jingyi, YANG Min, Telepresence Interaction by Touching Live Video Images, arXiv:1512.04334, 2015.

2.       WU Yuwei, YUAN Junsong, ZHANG Jian, LI Peihua and JIA Yunde, Manifold Kernel Sparse Representation of Symmetric Positive Definite Matrices and Its Applications, IEEE Transactions on Image Processing (T-IP), 24(11): 3729-3741, 2015.

3.       YANG Min, PEI mingtao, WU Yuwei, and JIA Yunde, Learning Online Structural Appearance Model for Robust Object Tracking, SCEINCE CHINA Information Science, 58(3): 1-14, 2015.

4.       WU Xinxiao, WANG Han, LIU Cuiwei, and JIA Yunde, Cross-view Action Recognition over Heterogeneous Feature Spaces, IEEE Transactions on Image Processing(T-IP), 24(11): 4096-4108, 2015.

5.       QIN Xiameng, SHEN Jianbing, MAO Xiaoyang, LI Xuelong, and JIA Yunde, Robust Match and Fusion using Optimization, IEEE Transactions on Cybernetics (T-CYB), 45(8):1549-1560, 2015.

6.       WU Yuwei, PEI Mingtao, YANG Ming, YUAN Junsong, and JIA Yunde, Robust Discriminative Tracking via Landmark-based Label Propagation, IEEE Transactions on Image Processing (T-IP), 24(5): 1510-1523, 2015.

7.       DONG Zhen, WU Yuwei, PEI Mingtao and JIA Yunde, Vehicle Type Classification Using Semi-Supervised Convolutional Neural Network, IEEE Transactions on Intelligent Transportation Systems (T-ITS) 16(4): 2247-2256, 2015.

8.       QIN Xiameng, SHEN Jianbing, MAO, LI Xuelong, and JIA Yunde, Dense Correspondence using Structured-Patch Optimization, IEEE Transactions on Multimedia (T-MM), 17(3):295-306, 2015.

(2014)

1.       WANG Han, WU Xinxiao, FENG Yang, and JIA Yunde, Video Annotation via Image Groups from the Web, IEEE Transactions on Multimedia (T-MM), 16(5):1282-1291, 2014.

2.       KONG Yu, JIA Yunde, and FU Yun, Interactive Phrases: Semantic Descriptions for Human Interaction Recognition, IEEE Transactions on Pattern Recognition and Machine Intelligence (T-PAMI), 36(9):1775-1788, 2014.

3.       WU Yuwei, MA Bo, YANG Min, ZHANG Jian, and JIA Yunde, Metric Learning based Structural Appearance Model for Robust Visual Tracking, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 24(5):865-877, 2014.

4.       WANG Han, LIU Xiabi, WU Xinxiao, and JIA Yunde, Cross-Domain Structural Model for Video Event Annotation via Web Images, Multimedia Tools and Applications, 1-18, 2014.

5.       KONG Yu, LIANG Wei, DONG Zhen, and JIA Yunde, Recognition Human interaction from Videos by a Discriminative Model, IET Computer Vision, 8(4):277–286, 2014.

6.       YANG Jiaolong, LI Hongdong, and JIA Yunde, Optimal Essential Matrix Estimation in the Presence of Outliers, European Conference on Computer Vision (ECCV2014), Switzerland, 2014.

(2013)

1.       WU Xinxiao, XU Dong, DUAN Lixin, LUO Jiebo, and JIA Yunde, Action recognition using multi-level features and latent structural SVM, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 23(8):1422-1431, 2013.

2.       WU Yuwei, WANG Yuanquan, and JIA Yunde, Adaptive Diffusion Flow Active Contours for Image Segmentation, Computer Vision and Image Understanding (CVIU), 117(10):1421-1435, 2013.

3.       WU Yuwei, WANG Yuanquan, and JIA Yunde, Segmentation of the left ventricle in cardiac cine MRI using shape-constrained active contours with a novel external force, Computer Vision and Image Understanding (CVIU), 117(9):990-1003, 2013.

4.       YANG Jiaolong, LI Hongdong, and JIA Yunde, Globally-Optimal ICP: Solving the 3D Registration Problem Efficiently and Globally Optimally, IEEE International Conference on Computer Vision (ICCV2013), Australia, 2013.

5.       WU Xinxiao, WANG Han, LIU Cuiwei, and JIA Yunde, Cross-view Action Recognition over Heterogeneous Feature Spaces, IEEE International Conference on Computer Vision (ICCV2013), Australia, 2013.

6.       SONG Xi, WU Tianfu, JIA Yunde and ZHU Songchun, Discriminatively Trained And-Or Tree Models for Object Detection, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR2013), USA, 2013.

(2012)

1.       ZHAO Youdong, GONG Haifeng, JIA Yunde, and ZHU Song-Chun, Background Modeling by Subspace Learning on Spatio-Temporal Patches, Pattern Recognition Letters 33(9):1134-1147, 2012.

2.       CHEN Lei, JIA Yunde, and LI Mingxiang, An FPGA-Based RGBD Imager, Machine Vision and Applications, Machine Vision and Applications (MVA), 23(3):513-525, 2012.

3.       KONG Yu, JIA Yunde and FU Xin, Learning Human Interaction by Interactive Phrases, European Conference on Computer Vision (ECCV2012), Italy, 2012.

4.       WU Xinxiao and JIA Yunde, View-Invariant Action Recognition using Latent Kernelized Structural SVM, European Conference on Computer Vision (ECCV2012), Italy, 2012.

5.       ZHAO Youdong, SONG Xi and JIA Yunde, On the Dimensionality of Video Bricks under Varying Illumination, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR2012), USA, June 2012.

6.       JIA Yunde and QIN Xiameng, A Stereovision System with an Embedded Calibration Tool, The Intelligent Vehicles Symposium (IV2012), Spain, June 2012.[pdf]

(2011)

1.       KONG Yu, ZHANG Xiaoqin, HU Weiming, and JIA Yunde, Learning Adaptive Codebook for Action Recognition, Pattern Recognition Letter 32(8):1178-1186, 2011.

2.       PEI Mintao, JIA Yunde, and ZHU Songchun, Parsing Video Events with Goal inference and Intent Prediction, IEEE International Conference on Computer Vision (ICCV2011), Spain, 2011.

3.       SHEN Jianbing, YANG Xiaoshan, JIA Yunde and LI Xuelong, Intrinsic Images Using Optimization, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR2011), USA, June 2011.

(2010)

1.       WU Xinxiao, JIA Yunde and LIANG Wei, Incremental Discriminant-Analysis of Canonical Correlations for Action Recognition, Pattern Recognition, 43(12):4190-4197, 2010.

2.       HAN Lei, WU Xinxiao, LIANG Wei, HOU Guangmin and JIA Yunde, Discriminative Human Action Recognition in the Learned Hierarchical Manifold Space, Imaging and Vision Computing (IVC), 28(5):836–849, 2010.

3.       LI Shanqing and JIA Yunde, A Multimodal Labeling Interface for Wearable Computing, International Conference on Intelligent User Interface (IUI2010), HK, Feb. 2010.