视频简介

教育经历

  • 2010年8月至2016年1月:清华大学,博士
  • 2014年11月至2015年6月:美国西北大学,访问学生
  • 2006年9月至2010年7月:北京理工大学,学士

工作经历

  • 2020年7月-至今,中国人民大学高瓴人工智能学院,准聘副教授
  • 2019年10月-2020年1月,微软亚洲研究院,铸星计划访问研究员
  • 2018年10月-2020年6月,中国科学院软件研究所,副研究员
  • 2016年4月-2018年9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

学生要求

对研究有兴趣;具备一定的编程能力;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

学术成果

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

2019
Spatiotemporal Pyramid Pooling in 3D Convolutional Neural Networks for Action Recognition
Cheng Cheng, Pin Lv, and Bing Su
IEEE International Conference on Image Processing (ICIP), 2018.

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

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

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

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

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

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

Learning Low-Dimensional Temporal Representations
Learning Low-Dimensional Temporal Representations
International Conference on Machine Learning (ICML), 2018, pp. 4761-4770. (CCF A)

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

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

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

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

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

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

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

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

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

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

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

荣誉奖励

  • 中科院软件所优秀科技人才计划,2019年
  • 中国科学院青年创新促进会会员,2019年

社会兼职

  • 期刊评审员:TPAMI,TIP,TCSVT
  • 会议评审员:ICML 2020, NeurIPS 2020,ICME 2020

contact

电话:--

邮箱:bingsu@ruc.edu.cn

个人网页:--

办公地址:--