中科院计算所视觉信息处理与学习组
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 副研究员

Email:changhong [at] ict dot ac dot cn; hong.chang [at] vipl dot ict dot ac dot cn

视觉建模组致力于研究新的机器学习方法与技术,以解决现实的计算机视觉问题,主要包括图像视频的表示、理解、预测和增强,以及面向下一代智能视频监控的目标(特别是行人)检测、跟踪、识别和检索。过去的几年中,视觉建模组在相关领域会议和期刊上发表多篇论文。最近,该组成员获得ECCV’2018行人检测竞赛冠军,以及ICME‘’18铂金最佳论文奖。
研究内容

●  机器学习的模型和算法,特别是

1)    度量学习
2)    少样本学习
3)    半监督/弱监督学习
4)    深度学习


●  图像/视频表示与理解

1)    属性学习
2)    视觉关系检测
3)    组合语义学习 
 

●  图像/视频生成与增强

1)    图像生成
2)    视频预测
3)    图像/视频超分辨率 
 

●  目标检测、跟踪与识别

1)    行人再识别
2)    目标(特别是行人)检测
3)    单大目标/多目标跟踪


部分论文

刊物论文

1.    Kongming Liang, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen, "Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework," IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2019.(Accepted)2018 【pdf】

2.    Bingpeng Ma, Rui Huang, Lei Qin, "VOD: A Novel Image Representation for Head Yaw Estimation," Neurocomputing, vol. 148, pp. 455-466, 2015. 【pdf】

3.    Hao Liu, Bingpeng Ma, Lei Qin, Junbiao Pang, Chunjie Zhang, Qingming Huang, "Set-Label Modeling and Deep Metric Learning on Person Re-Identification," Neurocomputing, vol. 151, no. 3, pp. 1283-1292, 2015. 【pdf】

4.    Bingpeng Ma, Yu Su, Frederic Jurie, "Covariance Descriptor Based on Bio-Inspired Features for Person Re-Identification and Face Verification," Image and Vision Computing, vol. 32, no. 6-7, pp. 379-390, 2014. 【pdf】

5.    Bingpeng Ma, Annan Li, Xiujuan Chai, Shiguang Shan, "CovGa:A Novel Descriptor Based on Symmetry of Regions for Head Pose Estimation," Neurocomputing, vol. 143, pp. 97-108, 2014. 【pdf】

6.    Zhen Cui, Hong Chang, Shiguang Shan, Bingpeng Ma, "Joint Sparse Representation for Video-Based face Recognition," Neurocomputing, 2014. 【pdf】

7.    Wei Zheng, Hong Chang, Luhong Liang, Haoyu Ren, Shiguang Shan, Xilin Chen, “Strip features for fast object detection for fast object detection,” IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, vol.43, no.6, pp.1898-1912,Dec.2013. 【pdf】

8.    Wei Zheng, Hong Chang, Luhong Liang, Haoyu Ren, Shiguang Shan, Xilin Chen, "Strip Features for Fast Object Detection," IEEE Transactions on Cybernetics, vol. 43(6), pp. 1898, 2013. 【pdf】

9.    Bingpeng Ma, Xiujuan Chai, Tianjiang Wang, "A Novel Feature Descriptor Based on Biologically Inspired Feature for Head Pose Estimation," Neurocomputing, vol. 115, pp. 1-10, 2013. 【pdf】

10.    Deming Zhai, Hong Chang, Shiguang Shan, Xilin Chen, Wen Gao, "Multi-View Metric Learning with Global Consistency and Local Smoothness," ACM Transactions on Intelligent Systems and Technology, Volume 3 Issue 3, May 2012. 【pdf】

11.    Bo Li, Hong Chang, Shiguang Shan, Xilin Chen, “Low-Resolution Face recognition via Coupled Locality Preserving Mappings,” IEEE Signal Processing Letters, vol.16, no.11, pp.20-23,Nov.2009. 【pdf】

12.    Xiaopeng Hong, Hong Chang, Shiguang Shan, Bineng Zhong, Xilin Chen, Wen Gao, “Sigma Set Based Implicit Online Learning For Object Tracking,” IEEE Signal Processing Letters, vol.17, no.9, pp.807-810,Sept.2010.

13.    Bo Li, Hong Chang, Shiguang Shan, Xilin Chen, “Aligning Coupled Manifolds for Face Hallucination,” IEEE Signal Processing Letters, vol.17, no.1, pp. 957-960 ,Jan.2010. 【pdf】

会议论文

1.    Liqiang Bao, Bingpeng Ma, Hong Chang, Xilin Chen, Masked Graph Attention Network for Person Re-identification. International Workshop conjunction with IEEE Computer Vision and Pattern Recognition(CVPR), June 2019. (Accepted)

2.    Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen, “Interaction-and-Aggregation Network for Person Re-identification,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Feb. 2019. ( Accepted).

3.    Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen, “VRSTC: Occlusion-Free Video Person Re-Identification,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Feb. 2019. ( Accepted)

4.    Ruibing Hou, Hong Chang, Bingpeng Ma and Xilin Chen, "Video Prediction with Bidirectional Constraint Network," 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), pp. 1-8, Lille, France, May 14-18, 2019.(Accepted)

5.    Liqiang Bao, Bingpeng Ma, Hong Chang, Xilin Chen, Preserving Structural Relationships for Person Re-identification. International Workshop conjunction with IEEE International Conference on Multimedia and Expo(ICME), July 2019. (Accepted)

6.    Kongming Liang, Yuhong Guo, Hong Chang, Xilin Chen, "Visual Relationship Detection with Deep Structural Ranking," AAAI Conference on Artificial Intelligence(AAAI2018), New Orleans, Louisiana, USA, 2018. 【pdf】

7.    Furong Xu, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, "Style Transfer with Adversarial Learning for Cross-Dataset Person Re-identification," Asian Conference on Computer Vision 2018(ACCV2018), 2-6 Dec. 2018, Perth Western Australia. 【pdf】

8.    Shen Li, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, "Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking," IEEE International Conference on Multimedia and Expo(ICME2018) 【pdf】

9.    Xiaqing Xu, Bingpeng Ma, Hong Chang, Xilin Chen, "Siamese Recurrent Architecture for Visual Tracking," IEEE International Conference on Image Processing(ICIP2017), 2017. 【pdf】

10.    Kongming Liang, Yuhong Guo, Hong Chang, Xilin Chen, "Incomplete Attribute Learning with Auxiliary Labels," International Joint Conference on Artificial Intelligence(IJCAI2017), 2017. 【pdf】

11.    Xuesong Deng, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, "Deep Second-Order Siamese Network for Pedestrian Re-Identification," Asian Conference on Computer Vision(ACCV2016), pp. 321-337, 2016. 【pdf】

12.    Jianfeng He, Bingpeng Ma, Shuhui Wang, Yugui Liu, Qingming Huang, "Cross-Modal Retrieval by Real Label Partial Least Squares," ACM Multimedia(ACMMM2016), pp. 227-231, 2016. 【pdf】

13.    Liang Zhang, Bingpeng Ma, Guorong Li, Qingming Huang, Qi Tian, "PL-Ranking:A Novel Ranking Method for Cross-Modal Retrieval," ACM Multimedia(ACMMM2016), pp. 1355-1364, 2016. 【pdf】

14.    Mingquan Ye, Hong Chang, Xilin Chen, "Online Visual Tracking Via Coupled Object-Context Dictionary," British Machine Vision Conference(BMVC2015), Swansea, UK, 2015. 【pdf】

15.    Kongming Liang, Hong Chang, Shiguang Shan, Xilin Chen, "A Unified Multiplicative Framework for Attribute Learning," IEEE International Conference on Computer Vision(ICCV2015), Santiago, Chile, 2015. 【pdf】

16.    Bingpeng Ma, Qian Li, Hong Chang, “Gaussian descriptor based on local features for person re-identification,” Workshop on Asian Conference on Computer Vision(ACCV2014), Singapore, Nov.2014. 【pdf】

17.    Bingpeng Ma, Qian Li, Hong Chang, "Gaussian Descriptor Based on Local Features for Person Re-Identification," ACCV Workshop on HIS, pp. 505-518, 2014. 【pdf】

18.    Deming Zhai, Hong Chang, Xilin Chen, Wen Gao, “Instance-Specific Canonical Correlation Analysis for Pose Alignment,” in Proceedings of IEEE International Conference on Image Processing(ICIP2013), Melbourne, Australia, Sept.2013. 【pdf】

19.    Xing Yan, Hong Chang, Xilin Chen, “Temporally Multiple Dynamic Textures Synthesis Using Piecewise Linear Dynamic Systems,” in Proceedings of IEEE International Conference on Image Processing(ICIP2013), Melbourne, Australia, Sept.2013. 【pdf】

20.    Deming Zhai, Hong Chang, Yi Zhen, Xianming Liu, Xilin Chen, Wen Gao, “Parametric Local Multimodal Hashing for Cross-view Similarity Search,” in Proceedings of The 23rd International Joint Conference on Artificial Intelligence(IJCAI2013), Beijing, Aug.2013. 【pdf】


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

  • 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