李兵

李兵  /  

  • 职  称: 正高级
  • 电子邮件: bing.li@ia.ac.cn

个人简历

姓名

李兵

性别

联系方式

bli@nlpr.ia.ac.cn

专业技术职务

研究员

部门/实验室

多模态人工智能系统全国重点实验室

通讯地址

北京市海淀区中关村东路95号

邮编

100190

研究领域

网络多媒体内容理解与安全,图像与视频内容理解

教育背景

2004-09--2009-07   北京交通大学   博士
2000-09--2004-07   北京交通大学   学士

工作简历

2018-11~现在, 中国科学院自动化研究所, 研究员
2013-11~2018-10,中国科学院自动化研究所, 副研究员
2011-07~2013-10,中国科学院自动化研究所, 助理研究员
2009-07~2011-06,中国科学院自动化研究所, 博士后

兼职经历

2019-08-30-今,人民网技术委员会, 委员
2015-12-31-2018-12-31,国际SCI期刊Neurocomputing的Associate Editor, 
2015-11-17-2020-11-17,中国人工智能学会智能服务专委会委员, 

发表论文

(1) Anisotropic Convolution for Image Classification, IEEE TIP, 2020, 通讯作者
(2) Web Objectionable Video Recognition Based on Deep Multi-Instance Learning with Representative Prototypes Selection, IEEE TCSVT, 2020, 通讯作者
(3) Object Relational Graph with Teacher-Recommended Learning for Video Captioning, CVPR, 2020, 第 4 作者
(4) Graph convolutional network with structure pooling and joint-wise channel attention for action recognition, Pattern Recognition, 2020, 通讯作者
(5) Anomaly Detection Using Local Kernel Density Estimation and Context-Based Regression, IEEE TKDE, 2019, 第 3 作者
(6) Multimodal Semantic Attention Network for Video Captioning, ICME, 2019, 通讯作者
(7) Knowledge Distillation via Instance Relationship Graph, CVPR, 2019, 通讯作者
(8) Asymmetric 3D Convolutional Neural Networks for Action Recognition, Pattern Recognition, 2019, 第 3 作者
(9) Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition, AAAI, 2018, 第 3 作者
(10) Spatio-Temporal Self-Organizing Map Deep Network for Dynamic Object Detection From Videos, CVPR, 2017, 第 3 作者
(11) Multi-View Multi-Instance Learning Based on Joint Sparse Representation and Multi-View Dictionary Learning, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017, 第 1 作者
(12) Salient Object Detection via Structured Matrix Decomposition, IEEE Trans. on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2017, 第 2 作者
(13) Multi-Cue Illumination Estimation via Tree-Structured Group Joint Sparse Representation, International Journal of Computer Vision (IJCV), 2016, 第 1 作者
(14) Multi-Instance Multi-label Learning Combining Hierarchical Context and Its Application to Image Annotation, IEEE Trans. On Multimedia (IEEE TMM), 2016, 通讯作者
(15) Horror Image Recognition Based on Context-Aware Multi-Instance Learning, IEEE Trans. on Image Processing (IEEE TIP), 2015, 第 1 作者
(16) Evaluating Combinational Illumination Estimation Methods on Real-World Images, IEEE Trans. On Image Processing (IEEE TIP), 2014, 第 1 作者
(17) RGBD Salient Object Detection: A Benchmark and Algorithms, European Conference on Computer Vision (ECCV), 2014, 通讯作者
(18) Illumination Estimation based on Bilayer Sparse Coding, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013, 第 1 作者
(19) Salient Object Detection via Low-Rank and Structured Sparse Matrix Decomposition, AAAI Conference on Artificial Intelligence (AAAI), 2013, 通讯作者
(20) Visual Saliency Map from Tensor Analysis, AAAI Conference on Artificial Intelligence (AAAI), 2012, 第 1 作者
(21) Context-aware Affective Images Classification based on Bilayer Sparse Representation, ACM International Conference on Multimedia (ACM MM), 2012, 第 1 作者
(22) Evaluating combinational color constancy methods on real-world images, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2011, 第 1 作者
(23) Context-Aware Multi-Instance Learning based on Hierarchical Sparse Representation, IEEE, International Conference on Data Mining (ICDM), 2011, 第 1 作者
(24) A Supervised Combination Strategy for Illumination Chromaticity Estimation, ACM Trans. On Applied Perception, 2010, 第 1 作者

发表著作

(1) 图像理解:颜色认知计算, 清华大学出版社, 2013-12, 第 2 作者

科研项目

( 1 ) 院青年促进会项目, 主持, 部委级, 2017-01--2020-12
( 2 ) XXXXXXXXXX视频识别研究, 主持, 国家级, 2017-01--2020-12
( 3) 网络XX多媒体内容的智能解析与识别研究, 主持, 省级, 2018-11--2021-12
( 4 ) 基于目标行为的视频流内容安全分析与智能检索, 主持, 国家级, 2020-01--2023-12
( 5 ) 网络多媒体内容安全与智能风控, 主持, 部委级, 2020-01--2020-12