Li LIU (刘李)

I am an assistant professor at The Hong Kong University of Science and Technology (Guangzhou) in the AI Thrust. I am also an Affiliated Assistant Professor of the department of Computer Science & Engineering at The Hong Kong University of Science and Technology, Hong Kong. Previously, I graduated from Université Grenoble Alpes, Grenoble, France with a PhD, and I was a postdoc researcher at Toronto Metropolitan University, Toronto, Canada.

I worked on "AI for Social Good", and my research directions are multi-modal audio-visual speech processing, AI robustness and AI for healthcare.

Email / Google Scholar / Zhi Hu / GitHub

News

I have several open positions for high-quality PhD, master students, and research assistants. If you are interested, please contact me by avrillliu@hkust-gz.edu.cn.

09/2024, Congratulations on obtaining the Best Student Paper Award Finalist in ICSR 2024!

09/2024, two papers have been accepted by Neurips 2024.

08/2024, Congratulations on obtaining the General Project of the National Natural Science Foundation of China!

07/2024, Our paper on “Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning” has been accepted by ACM MM 2024.

06/2024, Congratulations on successful promotion to IEEE senior member.

04/2024, Our paper on “Bridge to Non-Barrier Communication: Gloss-Prompted Fine-Grained Cued Speech Gesture Generation with Diffusion Model” has been accepted by IJCAI 2024.

2/2024, Our paper on “Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition” has been accepted by The IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP).

12/2023, Our paper on “Label correction and sample correction for improving AI Robustness” has been accepted by ICASSP 2024.

11/2023, Congratulations! Our two papers were awarded as "The Second Shenzhen Excellent Science and Technology Papers 2023" Excellent Science and Technology Papers.

10/2023, I was assigned as the Area Chair of ICASSP 2024.

07/2023, two papers have been accepted by ACM MM 2023.

07/2023, one paper has been accepted by ICCV 2023.

06/2023, Congratulations on being awarded the Tencent AI Lab Rhino Bird Grant for 2023!

05/2023, Congratulations! Our paper "MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging" was early accepted by MICCAI 2023 (top 14%).

05/2023, three papers have been accepted by Interspeech 2023.

05/2023, I was assigned as the Session Chair of ICASSP 2023.

04/2023, one paper has been accepted by SIGIR 2023.

02/2023, four papers have been accepted by IEEE ICASSP 2023.

12/2022, one paper was published in IEEE TPAMI 2022.

12/2022, one paper was published in TMI 2022.

12/2022, Congratulations! Our two papers were awarded as "The Second Shenzhen Excellent Science and Technology Papers 2022" Excellent Science and Technology Papers.

11/2022, one paper was published in NeurIPS 2022.

10/2022, one paper was published in ECCV 2022.

06/2022, one paper was published in CVPR 2022.

03/2022, I was assigned as the Local Chair (China) ICASSP 2022.

Selected Publications

Topic 1. I began to conduct research on the automatic recognition of French/English Cued Speech (CS) during the PhD and Postdoc periods. I proposed the first Mandarin Chinese CS System, which gains good feedback from international reviewers and CS society. By successfully introducing the deep neural network models into CS automatic recognition for the first time, and conducting research on the CS asynchronous fusion, my work has made great progress in solving the challenging problems in this field compared with the previous SOTA works.

Re-synchronization using the Hand Preceding Model for Multi-modal Fusion in Automatic Continuous Cued Speech Recognition
Li Liu, Gang Feng, Denis Beautemps, Xiao-Ping Zhang
IEEE Transactions on Multimedia 2020 | paper

A Pilot Study on Mandarin Chinese Cued Speech
Li Liu, Gang Feng
American Annals of the Deaf 2019 | paper

Inner Lips Feature Extraction based on CLNF with Hybrid Dynamic Template for Cued Speech
Li Liu, Gang Feng, Denis Beautemps
EURASIP Journal on Image and Video Processing 2017 | paper

Automatic Temporal Segmentation of Hand Movements for Hand Positions Recognition in French Cued Speech
Li Liu, Gang Feng, Denis Beautemps
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2018 | paper

Automatic Dynamic Template Tracking of Inner Lips based on CLNF
Li Liu, Gang Feng, Denis Beautemps
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2017 | paper

Automatic Detection of the Temporal Segmentation of Hand Movements in British English Cued Speech
Li Liu, Jianze Li, Gang Feng, Xiao-Ping Zhang
Conference of the International Speech Communication Association (Interspeech) 2019 | paper

Visual Recognition of Continuous Cued Speech Using a Tandem CNN-HMM Approach
Li Liu, Thomas Hueber, Gang Feng, Denis Beautemps
Conference of the International Speech Communication Association (Interspeech) 2019 | paper

Objective Hand Complexity Comparison between Two Mandarin Chinese Cued Speech Systems
Li Liu, Gang Feng, Xiaoxi Ren, Xianping Ma
International Symposium on Chinese Spoken Language Processing (ISCSLP) 2022 | paper

A Novel Resynchronization Procedure for Hand-lips Fusion applied to Continuous French Cued Speech Recognition
Li Liu, Gang Feng, Denis Beautemps, Xiao-Ping Zhang
European Signal Processing Conference (EUSIPCO) 2019 | paper

Inner Lips Parameter Estimation based on Adaptive Ellipse Model
Li Liu, Gang Feng, Denis Beautemps
International Conference on Auditory-Visual Speech Processing (AVSP) 2017 | paper

Extraction Automatique de Contour de Lèvre à partir du Modèle CLNF
Li Liu, Gang Feng, Denis Beautemps
Journées d'Etudes sur la Parole (JEP) 2016 | paper

Acoustic-to-Articulatory Inversion based on Speech Decomposition and Auxiliary Feature
Jianrong Wang, Longxuan Zhao, Shanyu Wang, Ruiguo Yu, Li Liu*
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022
(* corresponding author) | paper

Residual-guided Personalized Speech Synthesis Based on Face Image
Jianrong Wang, Ge Zhang, Zhenyu Wu, Xuewei Li, Li Liu*
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022
(* corresponding author) | paper

Cross-Modal Knowledge Distillation Method for Automatic Cued Speech Recognition
Jianrong Wang, Ziyue Tang, Xuewei Li, Mei Yu, Qiang Fang, Li Liu*
Conference of the International Speech Communication Association (Interspeech) 2021
(* corresponding author) | paper

An Attention Self-supervised Contrastive Learning based Three-stage Model for Hand Shape Feature Representation in Cued Speech
Jianrong Wang, Nan Gu, Mei Yu, Xuewei Li, Qiang Fang, Li Liu*
Conference of the International Speech Communication Association (Interspeech) 2021
(* corresponding author) | paper

Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition
Jianrong Wang, Tong Wu, Shanyu Wang, Mei Yu, Qiang Fang, Ju Zhang, Li Liu*
International Conference on Pattern Recognition (ICPR) 2021
(* corresponding author) | paper

MVNet: Memory Assistance and Vocal Reinforcement Network for Speech Enhancement
Jianrong Wang, Xiaomin Li, Xuewei Li, Mei Yu, Qiang Fang, Li Liu*
International Conference on Neural Information Processing (ICONIP) 2022
(* corresponding author) | paper

Topic 2. Apart from the above audio visual speech processing, I also investigated Computer Vision, AI security, few-shot learning and other related research applications.

WebUAV-3M: A Benchmark Unveiling the Power of Million-Scale Deep UAV Tracking
Chunhui Zhang, Guanjie Huang, Li Liu*, Shan Huang, Yinan Yang, Xiang Wan, Shiming Ge, Dacheng Tao
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022
(* corresponding author) | paper | data and code

Contrastive Self-supervised Meta-Learning for pre-training Ultrasound Image Analysis Model
Yixiong Chen, Chunhui Zhang, Chris Ding, Li Liu*
IEEE Transactions on Medical Imaging (TMI) 2022
(* corresponding author) | paper | code

Pre-activation Distributions Expose Backdoor Neurons
Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu*
Conference on Neural Information Processing Systems (NeurIPS) 2022
(* corresponding author) | paper | code

Data-free Backdoor Removal Based on Channel Lipschitzness
Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu*
European Conference on Computer Vision (ECCV) 2022
(* corresponding author) | paper | code

CG-ATTACK: Modeling the Conditional Distribution of Adversarial Perturbations to Boost Black-Box Attack
Feng Yan, Baoyuan Wu, Yanbo Fan, Li Liu, Zhifeng Li, Shutao Xia
Conference on Computer Vision and Pattern Recognition (CVPR) 2022 | paper | code

Effective Sample Pair Generation for Ultrasound Video Contrastive Representation Learning
Yixiong Chen, Chunhui Zhang, Li Liu*, Cheng Feng, Changfeng Dong, Yongfang Luo, Xiang Wan
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021
(* corresponding author) | paper (13% oral) | code

HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining
Chunhui Zhang, Yixiong Chen, Li Liu*, Qiong Liu, Xi Zhou
Asian Conference on Computer Vision (ACCV) 2022
(* corresponding author) | paper | code

Self-supervised Depth Estimation via Implicit Cues from Videos
Jianrong Wang, Ge Zhang, Zhenyu Wu, Xuewei Li, Li Liu*
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2021
(* corresponding author) | paper

Multi-Modal Active Learning for Automatic Liver Fibrosis Diagnosis based on Ultrasound Shear Wave Elastography
Lufei Gao, Ruisong Zhou, Changfeng Dong, Cheng Feng, Zhen Li, Xiang Wan, Li Liu*
IEEE International Symposium on Biomedical Imaging (ISBI) 2021
(* corresponding author) | paper

Semi-Supervised Active Learning for COVID-19 Lung Ultrasound Multi-symptom Classification
Lei Liu, Wentao Lei, Yongfang Luo, Cheng Feng, Xiang Wan, Li Liu*
International Conference on Tools with Artificial Intellignce (ICTAI) 2020
(* corresponding author) | paper

Research Grants

Tencent AI Lab Rhino Bird Grant 2023 (PI)
300k RMB.

Young Scientists Fund of the Natural Science Foundation of China (PI)
300k RMB, Grant No. 62101351, 2022-01 to 2024-12.

Young Scientists Fund of the Natural Science Foundation of Guangdong Province (PI)
100k RMB, Grant No. 2020A1515110376, 2020-10 to 2023-09.

Shenzhen Outstanding Scientific and Technological Innovation Talents PhD Startup Project (PI)
300k RMB, Grant No. RCBS20210609104447108, 2022-04 to 2024-04.

Alibaba Innovative Research (PI)
500k RMB, 2022-04 to 2023-04.

Tencent Technology Venture Philanthropy Program (PI)
300k RMB, 2022-06 to 2023-06. (30 out of 307 projects)

Shenzhen Key Project-Basic Research Special Project (Natural Science Fund)
2000k RMB, 2023-01 to 2026-12.

Teaching

Artificial Intelligence in Medical Imaging and Health (course code: CSC4080 and MDS6001)
The Chinese University of Hong Kong, Shenzhen (CUHK-SZ), Jan. - May. 2022.

Other Services

Member of the Machine Learning for Signal Processing Technical Committee (MLSP-TC) of the IEEE Signal Processing Society, Chair of the election subcommittee, 2024-

ICIG 2023, Area Chair.

ICASSP 2022, China-site Local Chair.

Member of the Institute of Electrical and Electronics Engineers (IEEE Member).

Member of the Pattern Recognition and Machine Intelligence Committee of the Chinese Society of Automation.

Member of the Speech Dialogue and Auditory Processing Committee of CCF.

Member of the Women Science and Technology within the Chinese Society of Image and Graphics.

Reviewer for IEEE Signal Processing Magazine, IEEE/ACM Transactions on Audio, Speech and Language Processing, ICML, CVPR, ICASSP, Interspeech, and IJCAI.

Welcome to my website. Total Visitor: