Nan Pu
Ph.D. candidate / guest Office: media Lab Snellius, Leiden Inst. Advanced Computer Sciences Niels Bohrweg 1, 2333 CA Leiden the Netherlands |
About Me
I am now a third-year Ph.D. student under the supervision of Prof. Michael S. Lew, at the LIACS Media Lab group of Leiden University. Previously, I got Bachelor and Master degree from Soochow University and Southwest University in 2015 and 2018, respectively. |
[Github Hostpage] [Github Projects] [Google Scholar] [Chinese Blogs] |
Research Interest
Computer Vision: cross-modal person re-identification, image generation
Machine Learning: variational inference, deep bayes network, domain adaptation
Publications
2021
From Superficial to Deep: Language Bias driven Curriculum Learning for Visual Question Answering
Mingrui Lao, Yanming Guo, Yu Liu, Wei Chen, Nan Pu, Michael S. Lew
ACM International Conference on Multimedia (MM), 2021.
Feature Estimations based Correlation Distillation for Incremental Image Retrieval
Wei Chen, Yu Liu, Nan Pu, Weiping Wang, Li Liu, Michael S. Lew
IEEE Transactions on Multimedia (TMM), 2021.
[PDF]
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[PDF]
[Github]
Multi-Stage Hybrid Embedding Fusion Network for Visual Question Answering
Mingrui Lao, Yanming Guo, Nan Pu, Wei Chen, Yu Liu, Michael S. Lew
Neurocomputing, 423:541-550, 2021.
[PDF]
2020
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew
ACM International Conference on Multimedia (MM), 2020.
[PDF]
[Github]
2019
Domain Uncertainty Based on Information Theory for Cross-modal Hash Retrieval
Wei Chen, Nan Pu, Yu Liu, Erwin M. Bakker, Michael S. Lew
IEEE International Conference on Multimedia and Expo (ICME, Oral), 2019.
Learning a Domain-Invariant Embedding for Unsupervised Person Re-identification
Pu, Nan and Georgiou, TK and Bakker, Erwin M and Lew, Michael S
2019 International Joint Conference on Neural Networks (IJCNN, Oral), 2019.
2018 and before
Human action recognition in videos of realistic scenes based on multi-scale CNN feature
Zhou, Yongsheng and Pu, Nan and Qian, Li and Wu, Song and Xiao, Guoqiang
Pacific Rim Conference on Multimedia (PCM), 2017.
Acdademic Service
Journal reviewer for TCSVT, Neurocomputing, IJMIR, etc.