访问量:41553
 
李厚强
单位:电子工程与信息科学系
地址:合肥市四号信箱,中国科大六系
邮编:230027
电话:+86-551-63601340
个人主页: https://eeis.ustc.edu.cn/2010/0825/c2648a21007/page.htm
实验室介绍:
 
个人简历 Personal resume
李厚强,男,中国科学技术大学电子工程与信息科学系教授、博士生导师,国家“杰出青年基金”获得者,IEEE Fellow,多媒体计算与通信教育部-微软重点实验室主任。主要研究方向包括:计算机视觉与模式识别、视频编码与通信、人工智能与机器博弈等。发表学术论文200余篇,获授权发明专利60余项,有45项技术提案被视频编码国际标准接受。担任国际期刊IEEE TMM、IEEE TCSVT编委,担任国际会议ICME 2021大会共同主席和VCIP 2010程序委员会共同主席;获2019年国家技术发明二等奖(排名2)、2015年国家自然科学二等奖(排名2)、2012年安徽省科学技术一等奖(排名1),2013-2016连续4年获得中科院优秀研究生导师奖。
 
研究方向 Research direction
1、计算机视觉与模式识别
2、视频编码与通信
3、人工智能与机器博弈
 
招生信息 Enrollment information
要求学生具有扎实的数学基础、较强的软件编程能力和良好的外语水平
 
论文专著 The monograph
1) Unsupervised Deep Representation Learning for Real-Time Tracking - International Journal of Computer Vision (IJCV) - 2021 - 129(2)
2) Semantic Boundary Detection with Reinforcement Learning for Continuous Sign Language Recognition - IEEE TCSVT - 2021 - 31(3)
3) Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination - IEEE TCSVT - 2021 - 31(4)
4) Deep Relation Embedding for Cross-Modal Retrieval - IEEE Trans. Image Processing - 2021 - 30
5) An End-to-End Foreground-Aware Network for Person Re-Identification - IEEE Trans. Image Processing - 2021 - 30
6) Learning Diverse Models for End-to-end Ensemble Tracking - IEEE Trans. Image Processing - 2021 - 30
7) Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization - IEEE Trans. Multimedia - 2021 - 23
8) Single Shot Video Object Detector - IEEE Trans. Multimedia - 2021 - 23
9) Occupancy-Map-Based Rate Distortion Optimization and Partition for Video-Based Point Cloud Compression - IEEE TCSVT - 2021 - 31(1)
10) Neighborhood Pyramid Preserving Hashing - IEEE Trans. Multimedia - 2020 - 22(6)
11) Deep Learning-Based Video Coding: A Review and A Case Study - ACM Computing Survey - 2020 - 53(1)
12) Real-Time Correlation Tracking via Joint Model Compression and Transfer - IEEE Trans. Image Processing - 2020 - 29(12)
13) Improving Person Re-identification with Iterative Impression Aggregation - IEEE Trans. Image Processing - 2020 - 29(10)
14) Improving Sign Language Translation with Monolingual Data by Sign Back-Translation - CVPR - 2021 -
15) Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking - CVPR - 2021 -
16) Model-Aware Gesture-to-Gesture Translation - CVPR - 2021 -
17) SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations - SIGKDD - 2021 -
18) Transformation GAN for Unsupervised Image Synthesis and Representation Learning - CVPR - 2020 -
19) M-LVC: Multiple Frames Prediction for Learned Video Compression - CVPR - 2020 -
20) Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method - NeurIPS - 2020 -
 
报考意向 Ambition
 
 
COPYRIGHT 2007 中国科学技术大学研究生院、校学位办 All Rights Reserved 地址:安徽省合肥市金寨路96号 邮编:230026。
TEL:+86-551-63602928 FAX:+86-551-63602179 E-mail:gradschl@ustc.edu.cn