Jing Liu

Ph.D. Candidate

Fudan University

About Me

A Ph.D with a passion for exploring the vast potential of computer technology. My current research focuses on signal/multimedia processing, particularly multivariate time series analysis, sensor-based activity recognition, and video anomaly detection. Meanwhile, I have some experience in the internet and cloud computing industries.

Interests

Signal Processing
Activity Recognition
Video Anomaly Detection
Mutil-modal Affective Computing
Domain Generalization

Education

Ph.D. in Computer Science, 2019-2023

Fudan University
M.S. in Software Engineering, 2014-2017

University of Shanghai for Science and Technology
B.S. in Computer Science, 2010-2014

University of Shanghai for Science and Technology

Featured Publications

Jing Liu, Wei Zhu, Di Li, Xing Hu, Liang Song

April, 2023 SCIS

Domain Generalization with Semi-Supervised Learning for People-Centric Activity Recognition

The proposed DGSSL method effectively enhances people-centric activity recognition by addressing the domain shift problem in semi-supervised learning manner, with autoregressive discriminator for adversarial training and two reconstruction tasks, resulting in better performance and generalization than three state-of-the-art methods.

Jing Liu, Yang Liu, Wei Zhu, Xiaoguang Zhu, Liang Song

April, 2023 PR

Distributional and Spatial-Temporal Robust Representation Learning for Transportation Activity Recognition

This paper presents a parallel model called DSTRR for Transportation Activity Recognition (TAR), which combines automatic learning of statistical, spatial, and temporal features as a robust representation specific to TAR.

Jing Liu, Yang Liu, Di Li, Hanqi Wang, Xiaohong Huang, Liang Song

February, 2023 APIN

DSDCLA: Driving Style Detection via Hybrid CNN-LSTM with Multi-Level Attention Fusion

This paper proposes a attention-based CNN-LSTM model named DSDCLA for driving style detection.

Recent Publications

Domain Generalization with Semi-Supervised Learning for People-Centric Activity Recognition

Jing Liu, Wei Zhu, Di Li, Xing Hu, Liang Song

Distributional and Spatial-Temporal Robust Representation Learning for Transportation Activity Recognition

Jing Liu, Yang Liu, Wei Zhu, Xiaoguang Zhu, Liang Song

DSDCLA: Driving Style Detection via Hybrid CNN-LSTM with Multi-Level Attention Fusion

Jing Liu, Yang Liu, Di Li, Hanqi Wang, Xiaohong Huang, Liang Song

Research

Automated driving with vehicle-road cooperation

This research conducted experiments on Chongming Smart Island utilizing V2X communication for autonomous vehicles, focusing on vehicle-road coordination and testing its feasibility.

Experience

Cloud Solution Architect

Qiniu

May 2018 – Aug 2019 Shanghai

Worked on customizing cloud computing and smart solutions for key accounts (industries in internet, banking, media, etc.) by utilizing company’s products (e.g., server, storage, CDN, logging, and AI services).

Java Software Engineer

Ctrip

Jun 2017 – Apr 2018 Shanghai

Worked in the backend team on developing a system to provide customers with airport transfer booking services, incl. requirement review, technological design, coding, code review, and deployment.