EN

师资队伍

师资队伍

苏冰 准聘副教授
苏冰2016年博士毕业于清华大学,2010年本科毕业于北京理工大学。研究方向为计算机视觉、机器学习和模式识别,主要研究序列数据的特征表达学习、度量学习、时序结构分析及其在视频分析、动作分类中的应用。以第一作者在TPAMI、TIP、ICML、CVPR、ICCV等CCF A类期刊和会议上发表论文十余篇。

个人主页:

详细资料

教育经历

20108月至20161月:清华大学,博士

201411月至20156月:美国西北大学,访问学生

20069月至20107月:北京理工大学,学士

工作经历

2020年7-至今,中国人民大学高瓴人工智能学院,准副教授

201910-20201月,微软亚洲研究院,铸星计划访问研究员

201810-20206月,中国科学院软件研究所,副研究员

20164-20189月,中国科学院软件研究所,助理研究员

研究方向

序列距离学习:时序对齐、度量学习序列特征变换、特征降维最优传输时序结构分析

受限条件下的机器学习:小样本学习、迁移学习、联邦学习因果推理

计算机视觉应用:视频分类、动作识别、视觉与语义关联分析序列预测

对学生的培养要求

对研究有兴趣;具备一定编程能力;踏实、勤奋。欢迎对我研究方向感兴趣的同学与我联系。

科研项目

国家自然科学基金面上项目,批准号:61976206

项目名称:基于最优传输的序列距离学习理论和方法研究

国家自然科学基金青年科学基金项目,批准号:61603373

项目名称:基于最大化时序可分性的序列数据特征变换理论和方法研究

科研成果

1、期刊论文

— Bing Su and Ying Wu. “Learning Low-Dimensional Temporal Representations with Latent Alignments”, IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2019, accepted (CCF A)

Bing Su and Gang Hua. “Order-preserving Optimal Transport for Distances between Sequences”, IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2019, 41(12), pp. 2961-2974. (CCF A)

Bing Su, Xiaoqing Ding, Changsong Liu, and Ying Wu, "Heteroscedastic Max–Min Distance Analysis for Dimensionality Reduction", IEEE Trans. on Image Processing (TIP), 2018, 27(8), pp. 4052-4065. (CCF A)

Bing Su, Xiaoqing Ding, Hao Wang, and Ying Wu, "Discriminative Dimensionality Reduction for Multi-Dimensional Sequences", IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2018, 40(1), pp. 77-91. (CCF A)

Bing Su, Jiahuan Zhou, Xiaoqing Ding, and Ying Wu, "Unsupervised Hierarchical Dynamic Parsing and Encoding for Action Recognition ", IEEE Trans. on Image Processing (TIP), 2017, 26(12), pp. 5784-5799. (CCF A)

Bing Su, Xiaoqing Ding, Changsong Liu, Hao Wang, and Ying Wu, "Discriminative Transformation for Multi-dimensional Temporal Sequences", IEEE Trans. on Image Processing (TIP), 2017, 26(7), pp. 3579-3593. (CCF A)

2、会议论文

Jiahuan Zhou, Bing Su, and Ying Wu, "Online Joint Multi-Metric Adaptation from Frequent Sharing-Subset Mining for Person Re-Identification", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020. (CCF A)

Bing Su, Jiahuan Zhou, and Ying Wu, "Order-Preserving Wasserstein Discriminant Analysis", IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 9885-9894. (CCF A)

Bing Su and Ying Wu. “Learning Distance for Sequences by Learning a Ground Metric”, International Conference on Machine Learning (ICML), 2019, pp. 6015-6025. (CCF A)

Bing Su and Ying Wu. “Learning Low-Dimensional Temporal Representations”, International Conference on Machine Learning (ICML), 2018, pp. 4761-4770. (CCF A)

Jiahuan Zhou, Bing Su, and Ying Wu, " Easy Identification from Better Constraints: Multi-Shot Person Re-Identification from Reference Constraints", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 5373-5381. (CCF A)

Chenqin Cai, Pin Lv, and Bing Su, " Feature Fusion Network for Scene Text Detection", IEEE International Conference on Image Processing (ICIP), 2018.

Cheng Cheng, Pin Lv, and Bing Su, " Spatiotemporal Pyramid Pooling in 3D Convolutional Neural Networks for Action Recognition", IEEE International Conference on Image Processing (ICIP), 2018.

Bing Su and Gang Hua. “Order-preserving Wasserstein Distance for Sequence Matching”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1049-1057. (CCF A)

Bing Su, Jiahuan Zhou, Xiaoqing Ding, Hao Wang, and Ying Wu, "Hierarchical Dynamic Parsing and Encoding for Action Recognition", Proc. European Conf. on Computer Vision (ECCV), 2016, pp. 202-217. (CCF B)

Bing Su, Xiaoqing Ding, Changsong Liu, and Ying Wu. “Heteroscedastic Max-Min Distance Analysis”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 4539-4547. (CCF A)

Bing Su and Xiaoqing Ding. “Linear Sequence Discriminant Analysis: A Model-Based Dimensionality Reduction Method for Vector Sequences”, IEEE International Conference on Computer Vision (ICCV), 2013, pp. 889–896. (CCF A)

Bing Su, Xiaoqing Ding, Liangrui Peng, and Changsong Liu. “Cross-language Sensitive Words Distribution Map: A Novel Recognition-based Document Understanding Method for Uighur and Tibetan”, International Conference on Document Analysis and Recognition (ICDAR), 2013, pp. 255-259.

Bing Su, Xiaoqing Ding, Liangrui Peng, and Changsong Liu. “A Novel Baseline-independent Feature Set for Arabic Handwriting Recognition”, International Conference on Document Analysis and Recognition (ICDAR), 2013, pp. 1282-1286.

Bing Su, Liangrui Peng, and Xiaoqing Ding. SemiBoost-based Arabic character recognition method. Proc. SPIE 7874, Document Recognition and Retrieval XVIII (SPIE DRR), 2011.

社会兼职

期刊评审员:TPAMITIPTCSVT

会议评审员ICML 2020NeurIPS 2020ICME 2020

荣誉获奖

中科院软件所优秀科技人才计划,2019

中国科学院青年创新促进会会员,2019

检测到您当前使用浏览器版本过于老旧,会导致无法正常浏览网站;请您使用电脑里的其他浏览器如:360、QQ、搜狗浏览器的速模式浏览,或者使用谷歌、火狐等浏览器。

下载Firefox