Academic Qualification

Ph.D. in Pattern Recognition and Intelligent Systems, University of Chinese Academy of Sciences, China

M.S. in Opto-electronic Engineering, Hefei University of Technology, China

B.S. in Optical Information Science and Technology, Hefei University of Technology, China

Teaching Area

Digital Image Processing

Computer Vision

Research Area

Video Understanding and Analysis

Multi-modal Learning

Visual Perception, Reasoning and Planning for Robotics

3D Reconstruction, Generation and Editing

Large Vision-language Models

Working Experience

Mar. 2021 - Present, Assistant Professor, School of Computer Science and Engineering, Macau University of Science and Technology.

Mar. 2018 – Mar. 2021, Director of Computer Vision R&D, Long gang Institutes of Intelligent Video and Audio Technology, Shenzhen, China.

Sep. 2015 – Mar. 2018, post-doctoral researcher, Peking University.

Academic Publication (selected)

1.          Kan Huang, Nannan Li, Jiarong Huang, Chunwei Tian, “Exploiting Memory-based Cross-image Contexts for Salient Object Detection in Optical Remote Sensing Images”, IEEE Transactions on Geoscience and Remote Sensing, 2024.

2.          Fuqin Deng, Jiaming Zhong, Nannan Li, Lanhui Fu, Dong Wang, and Tin Lun Lam, "Exploring Cross-video Matching for Few-shot Video Classification via Dual-Hierarchy Graph Neural Network Learning ", Image and Vision Computing, 2023.

3.          Kan Huang, Chunwei Tian, Zhijing Xu, Nannan Li, Jerry Chun-Wei Lin, "Motion Context guided Edge-preserving Network for Video Salient Object Detection", Expert Systems with Applications, 2023.

4.          Ruochen Li, Nannan Li and Wenmin Wang, "Maximizing Mutual Information Inside Intra- and inter-modality for Audio-visual Event Retrieval ", International Journal of Multimedia Information Retrieval, 2022.

5.          Nannan Li, Jiaxing Zhong, Xiujun Shu, and Huiwen Guo, " Weakly-supervised Anomaly Detection in Video Surveillance via Graph Convolutional Label Noise Cleaning", Neurocomputing, 2021.

6.          Jingjia Huang, Nannan Li, Thomas Li, Shan Liu and Ge Li, "Spatial-Temporal Context-Aware Online Action Detection and Prediction", IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2019.

7.          Jia-xing Zhong, Nannan Li, Weijie Kong, Shan Liu, Thomas H.Li, and Ge Li, "Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection", International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

8.          Jingjia Huang, Zhangheng Li, Nannan Li, Shan Liu and Ge Li, "AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism", International Conference on Computer Vision (ICCV), 2019.

9.          Jingjia Huang, Nannan Li, Tao Zhang, Ge Li, Tiejun Huang, Wen Gao, "SAP: Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning," In AAAI Conference on Artificial Intelligence (AAAI), 2018.

10.      Jingjia Huang, Nannan Li, Jiaxing Zhong, Thomas Li, and Ge Li, "Online Action tube Detection via Resolving the Spatio-temporal Context Pattern", ACM Multimedia, 2018.

11.      Jia-xing Zhong, Nannan Li, Weijie Kong, Tao Zhang, Thomas Li and Ge Li, "Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector", ACM Multimedia, 2018.

12.      Nannan Li, Dan Xu, Zhenqiang Ying, Zhihao Li, and Ge Li, "Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking", Asian Conference on Computer Vision (ACCV), 2016.

Patents

1.ZL 2018 1 1298483.2, “An active video behavior detection system and method based on deep reinforcement learning”.

2.ZL 2018 1 1298487.0, “An online video behavior detection method based on spatiotemporal context analysis”.

3.ZL 2018 1 1298485.1, “A video behavior detection method based on shape-motion dual-stream information fusion”.