中科院计算所视觉信息处理与学习组

您所在的位置 / 科学研究

科学研究
视觉建模组

组  长:常虹

Email:changhong@ict.ac.cn

地  址:中国科学院计算技术研究所

Visual Modeling group focuses on R&D of innovative machine learning methodologies and technologie to solve real-world computer vision problems including large-scale image/video representation and enhancement, as well as object (especially human) detection, tracking, recognition and retrieval, oriented to next-generation intelligent video surveillance.
研究内容

Image and video representation and enhancement;
Object (especially human) detection;
Object (especially human) tracking;
Object (especially human) recognition;
Person re-identificaiton;

Current Research Projects:

  • 1. Research on deep coding methods for image and video feature representation;

  • 2. Technologies in large-scale object detection and recognition;

会议论文

1.    B. Li, H. Chang, S. Shan, X. Chen, W. Gao. Hallucinating Facial Images and Features. Proceedings of the Nineteenth International Conference on Pattern Recognition (ICPR), Tampa, Florida, USA, 7-11 December 2008.

2.    X. Hong, H. Chang, S. Shan, X. Chen and W. Gao. Sigma Set: A Small Second Order Statistical Region Descriptor. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

3.    B. Li, H. Chang, S. Shan, X. Chen. Locality preserving constraints for super resolution with neighbor embedding. Proceedings of the IEEE International Conference on Image Processing (ICPR), 2009.

4.    D. Zhai, H. Chang, B. Li, S. Shan, X. Chen, W. Gao. Semi-Supervised Discriminant Analysis via Spectral Transduction. Proceedings of the 20th British Machine Vision Conference (BMVC). London, UK, 2009.

5.    B. Li, H. Chang, S. Shan, and X. Chen. Coupled Metric Learning for Face Recognition with Degraded Images. Proceedings of the 1st Asian Conference on Machine Learning (ACML), 2009.

6.    X. Hong, H. Chang, X. Chen, and W. Gao. Boosted Sigma Set for Pedestrian Detection. Proceedings of the Twentyth International Conference on Pattern Recognition (ICPR), 2010.

7.    D. Zhai, H. Chang, B. Li, S. Shan, X. Chen, W. Gao. Manifold Alignment Via Corresponding Projections. Proceedings of the 21st British Machine Vision Conference (BMVC). Aberystwyth, UK, 2010.

8.    Y. Xie, H. Chang, Z. Li, L. Liang, X. Chen, D. Zhao. A unified framework for locating and recognizing human actions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2011.

9.    D. Zhai, H. Chang, Y. Zhen, X. Liu, X. Chen, W. Gao. Parametric Local Multimodal Hashing for Cross-view Similarity Search. Proceedings of the 23rd International Joint Conference on Arti cial Intelligence (IJCAI). Beijing, China , August 3-9, 2013.

视觉信息处理和学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse公众号

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号 京公网安备1101080060