I have recently been a postdoctoral researcher at the Multimedia and Human Understanding Group (MHUG) of the University of Trento, and am fortunate to work closely with Prof. Nicu Sebe and Prof. Zhun Zhong. Previously, I got Ph.D. degree from Leiden University in 2022, supervised by Prof. Michael Lew. During my Ph.D. study, I worked with Prof. Yu Liu.

My research interest includes continual/incremental/lifelong learning, federated learning, and popular computer vision tasks like person re-identification, visual question answering and novel/new category discovery.

🔥 News

  • 2024.09:  🎉🎉 One paper is accepted by NIPS 2024. Congratulation to Haiyang!

  • 2024.07:  🎉🎉 Two papers are accepted by ECCV 2024. Congratulation to Haiyang and Fengxiang!

  • 2024.02:  🎉🎉 Two papers are accepted by CVPR 2024. Congratulation to Yaqi!

  • 2023.08:  🎉🎉 Two papers are accepted by ACM MM 2023. Congratulation to Mingrui!

  • 2023.07:  🎉🎉 One paper is accepted by TKDE 2023. Congratulation to Yalan!

  • 2023.07:  🎉🎉 One paper is accepted by TPAMI 2023.

  • 2023.03:  🎉🎉 One paper is accepted by CVPR 2023.

📝 Publications

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
Haiyang Zheng*, Nan Pu*, Wenjing Li, Nicu Sebe, and Zhun Zhong.
Neural Information Processing Systems (NeurIPS), 2024.

Learning to Distinguish Samples for Generalized Category Discovery
Fengxiang Yang*, Nan Pu*, Wenjing Li, Zhiming Luo, Shaozi Li, Nicu Sebe, and Zhun Zhong
European Conference on Computer Vision (ECCV), 2024.

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
Haiyang Zheng*, Nan Pu*, Wenjing Li, Nicu Sebe, and Zhun Zhong
European Conference on Computer Vision (ECCV), 2024.

Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
Yu Liu, Yaqi Cai, Qi Jia, Binglin Qiu, Weimin Wang, Nan Pu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

Federated Generalized Category Discovery
Nan Pu, Wenjing Li, Xingyuan Ji, Yalan Qin, Sebe Nicu, Zhun Zhong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

FedVQA: Personalized Federated Visual Question Answering over Heterogeneous Scenes
Mingrui Lao, Nan Pu†, Zhun Zhong, Nicu Sebe, Michael S. Lew
ACM International Conference on Multimedia (MM), 2023.

Multi-Domain Lifelong Visual Question Answering via Self-Critical Distillation
Mingrui Lao, Nan Pu†, Yu Liu, Zhun Zhong, Erwin M. Bakker, Nicu Sebe, Michael S. Lew
ACM International Conference on Multimedia (MM), 2023.

Elastic Multi-view Subspace Clustering with Pairwise and High-order Correlations
Yalan Qin, Nan Pu, Hanzhou Wu
Transactions on Knowledge and Data Engineering (TKDE), 2023.

A Memorizing and Generalizing Framework for Lifelong Person Re-Identification
Nan Pu, Zhun Zhong, Nicu Sebe, Michael S. Lew
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery
Nan Pu, Zhun Zhong, Nicu Sebe
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

COCA: COllaborative CAusal Regularization for Audio-Visual Question Answering
Mingrui Lao, Nan Pu†, Yu Liu, Kai He, Erwin M. Bakker, Michael S. Lew
Association for the Advancement of Artificial Intelligence (AAAI), 2023.

Meta Reconciliation Normalization for Lifelong Person Re-identification
Nan Pu, Yu Liu, Wei Chen, Erwin M. Bakker, Michael S. Lew
ACM International Conference on Multimedia (MM), 2022.

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]

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]

Learning a Domain-Invariant Embedding for Unsupervised Person Re-identification
Nan Pu, T.K. Georgiou, Erwin M. Bakker and Michael S. Lew
2019 International Joint Conference on Neural Networks (IJCNN, Oral), 2019. [PDF]

(* denotes equal contribution and † denotes corresponding author)
🎉