人员简介

刘李

职务/职称

深圳市大数据研究院医疗大数据实验室研究科学家

研究方向

视听识别、医学影像、多媒体信息处理、机器学习、人工智能以及Cued Speech的发明和应用

电子邮箱

liuli@cuhk.edu.cn

教育背景

法国格勒诺布尔-阿尔卑斯大学电子工程博士学位

个人介绍

刘李博士目前在深圳市大数据研究院-香港中文大学深圳担任研究科学家。从2018年9月到2019年9月,她在加拿大多伦多瑞尔森大学(Ryerson University)计算机工程学院从事博士后研究。2015年10月到2018年9月,她在法国格勒诺布尔阿尔卑斯大学(Universite Grenoble Alpes)和法国国家科学研究中心(CNRS)共属的GIPSA-lab实验室攻读工程与机器学习博士,并于2018年9月11日获得博士学位。她现为国际电子电气工程师学会会员,信号处理协会会员以及中科院自动化所模式识别与人工智能专委会委员,中国女工委员会委员。担任IEEE/ACM Transactions on Audio, Speech, and Language Processing, Neurocomputing,Interspeech, SIGNAL等国际期刊和会议的审稿人。她的主要研究方向是:自动视听语音识别,医学影像,多媒体信息处理、小样本学习、机器学习与人工智能以及Cued Speech的发明和应用。

她现已以第一作者身份或通讯作者发表论文15篇,其中包括SCI论文 IEEE Transactions on Multimedia, EURASIP Journal on Image and Video Processing,SSCI论文American Annals of the Deaf,会议论文包括语音图像处理国际顶级会议ICASSP,语音处理国际顶级会议Interspeech,欧洲信号处理顶级会议Eusipco以及人工智能CCF级会议ICTAI,ICPR和ISBI。她在2017年荣获法国Sephora Berribi数学与计算机领域女性科学家奖学金 (全球当年共四位,法国与以色列各两位)。 同年获得法国语音协会(AFCP) 青年研究者奖学金。2016年,获得法国EEATS博士研究生院最佳报告奖(The best poster award)。

代表性论文

 

承担的科研项目(PI):

1. 带隐私保护的异步多模态线索语自动识别研究,国家自然科学基金委员会-青年基金项目,2022年1月至2024年12月,30万元。

2. 关于线索语中异步多模态融合与小样本识别问题的研究,广东省区域联合基金-青年基金项目,2020年10月至2023年9月,10万元。

3. 数据长尾分布场景下线索语多模态特征的无偏学习与联合学习研究,深圳市优秀科技创新人才培养-博士基础研究启动项目,2022年4月至2024年3月,30万元。

4. 联邦学习框架下的长尾分布和隐私泄漏问题的研究,阿里巴巴创新研究计划,2022年3月-2023年3月,50万元。

代表作:

[1] Feng, Yan, Baoyuan Wu, Yanbo Fan, Li Liu, Zhifeng Li, and Shutao Xia. "CG-ATTACK: Modeling the Conditional Distribution of Adversarial Perturbations to Boost Black-Box Attack." CVPR, 2022.

[2] Liu, Zhong, Huiying Wen, Ziqi Zhu, Qinyuan Li, Li Liu, Tianjiao Li, Wencong Xu. "Diagnosis of significant liver fibrosis in patients with chronic hepatitis B using a deep learning-based data integration network." Hepatology International (2022): 1-11.

[3] Jianrong Wang, Longxuan Zhao, Shanyu Wang, Ruiguo Yu, and Li Liu* , “Acoustic-to-Articulatory Inversion based on Speech Decomposition and Auxiliary Feature”, accepted by International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022.

[4] Jianrong Wang, Zixuan Wang, Xiaosheng Hu, Xuewei Li, Qiang Fang, Li Liu*, “Residual-guided Personalized Speech Synthesis Based on Face Image”, accepted by International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022.

[5] Jianrong Wang, Ge Zhang, Zhenyu Wu, Xuewei Li, and Li Liu*. “Self-supervised Depth Estimation via Implicit Cues from Videos,” International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.

[6] Jianrong Wang, Ziyue Tang, Xuewei Li, Mei Yu, Qiang Fang and Li Liu*. “Cross-Modal Knowledge Distillation Method for Automatic Cued Speech Recognition,” Conference of the International Speech Communication Association (Interspeech), 2021.

[7] Jianrong Wang, Nan Gu, Mei Yu, Xuewei Li, Qiang Fang and Li Liu*. “An Attention Self-supervised Contrastive Learning based Three-stage Model for Hand Shape Feature Representation in Cued Speech,” Conference of the International Speech Communication Association (Interspeech), 2021.

[8] Yixiong Chen, Chunhui Zhang, Li Liu*, Cheng Feng, Changfeng Dong, Yongfang Luo, Xiang Wan. “Effective Sample Pair Generation for Ultrasound Video Contrastive Representation Learning,” International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI, within 13% oral), 2021.

[9] Lufei Gao, Ruisong Zhou, Changfeng Dong, Cheng Feng, Zhen Li, Xiang Wan, and Li Liu*. “Multi-Modal Active Learning for Automatic Liver Fibrosis Diagnosis based on Ultrasound Shear Wave Elastography,” in Proc. IEEE International Symposium on Biomedical Imaging (ISBI), 2021.

[10] Li Liu, Gang Feng, Denis Beautemps, and Xiao-Ping Zhang. “Re-synchronization using the Hand Preceding Model for Multi-modal Fusion in Automatic Continuous Cued Speech Recognition,” IEEE Transactions on Multimedia, vol. 23, pp: 292-305, 2020.

[11] Lei Liu, Wentao Lei, Yongfang Luo, Cheng Feng, Xiang Wan, and Li Liu*. “Semi-Supervised Active Learning for COVID-19 Lung Ultrasound Multi-symptom Classification,” in IEEE Proc. International Conference on Tools with Artificial Intellignce (ICTAI), 2020.

[12] Li Liu, Jianze Li, Gang Feng, and Xiao-Ping Zhang. “Automatic Detection of the Temporal Segmentation of Hand Movements in British English Cued Speech,” in Proc. Conference of the International Speech Communication Association (Interspeech), pp: 2285-2289, 2019.

[13] Li Liu, and Gang Feng. “A Pilot Study on Mandarin Chinese Cued Speech,” American Annals of the Deaf, vol. 164, no. 4, pp: 496-518, 2019.

[14] Li Liu, Gang Feng, Denis Beautemps, and Xiao-Ping Zhang. “A Novel Resynchronization Procedure for Hand-lips Fusion applied to Continuous French Cued Speech Recognition,” in Proc. European Signal Processing Conference (EUSIPCO), pp: 1-5, 2019.

[15] Li Liu, Thomas Hueber, Gang Feng, and Denis Beautemps. “Visual Recognition of Continuous Cued Speech Using a Tandem CNN-HMM Approach,” in Proc. Conference of the International Speech Communication Association (Interspeech), pp: 2643-2647, 2018.

[16] Li Liu, Gang Feng, and Denis Beautemps. “Automatic Temporal Segmentation of Hand Movements for Hand Positions Recognition in French Cued Speech,” in Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp: 3061-306, 2018.

[17] Li Liu, Gang Feng, and Denis Beautemps. “Inner Lips Feature Extraction based on CLNF with Hybrid Dynamic Template for Cued Speech,” EURASIP Journal on Image and Video Processing, 2017: 88, 2017.

[18] Li Liu, Gang Feng, and Denis Beautemps. “Automatic Dynamic Template Tracking of Inner Lips based on CLNF,” in Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp: 5130–5134, 2017.

[19] Li Liu, Gang Feng, and Denis Beautemps. “Inner Lips Parameter Estimation based on Adaptive Ellipse Model,” in Proc. International Conference on Auditory-Visual Speech Processing (AVSP), 2017.

[20] Li Liu, Gang Feng, and Denis Beautemps. “Extraction Automatique de Contour de Lèvre à partir du Modèle CLNF,” in Proc. Journées d'Etudes sur la Parole (JEP), 2016.