Xiu-Shen WEI （魏秀参）

Xiu-Shen WEI                                                                                                                                             Ph.D., Professor School of Computer Science and Engineering, Nanjing University of Science and Technology Office: Room 4063-1 Email: weixsnjust.edu.cn or weixs.gmgmail.com

About Me

• From Jun. 2020, I am a Professor at Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, NJUST.

• From Oct. 2017 to Jun. 2020, I served as the Founding Director in Megvii Research Nanjing, Megvii Technology.

• In 2014 and 2018, I got my M.Sc. and Ph.D. degree in LAMDA Group at Nanjing University, advised by Prof. Zhi-Hua Zhou and Prof. Jianxin Wu, respectively. From Oct. 2016 to Oct. 2017, I was a visiting scholar in Prof. Chunhua Shen’s group at UoA, Australia.

• 欢迎有志投身人工智能领域的热忱学子报考我的研究生或本科科研训练及毕设！2023年招生开启！（联系邮箱：weixsnjust.edu.cn）

• 欢迎与我联系申请南京理工大学紫金博士后或博士后职位！（联系邮箱：weixsnjust.edu.cn）

Updates

• Nov. 1, 2022: We release a PyTorch-based library “Hawkeye” for Fine-Grained Recognition by deep CNNs on GitHub!

• Sept. 15, 2022: One paper about semi-supervised few-shot learning accepted by NeurIPS 2022.

• Aug. 21, 2022: Our team won the first place in the SnakeCLEF track of FGVC 2022 global competitions!

• Jul. 5, 2022: Two papers accepted by ECCV 2022.

• Jun. 6, 2022: Two papers accepted by SCIENCE CHINA Information Sciences (中国科学：信息科学).

• Mar. 10, 2022: One paper about automatic check-out accepted by IEEE TIP.

• Mar. 2, 2022: One paper about long-tailed instance segmentation accepted by CVPR 2022.

• Oct. 28, 2021: Our survey paper of Fine-Grained Image Analysis with Deep Learning was accepted by IEEE TPAMI.

• Apr. 28, 2020: We release a PyTorch-based library for unsupervised image retrieval by deep CNNs on GitHub!

• Jul. 6, 2019: Opened the “Awesome Fine-Grained Image Analysis – Papers, Codes and Datasets” homepage.

Research Interests

My research interests include some sub-fields of Computer Vision and Machine Learning:

• Deep Convolutional Neural Networks (DCNN) is a type of feed-forward artificial neural network where the individual neurons are tiled in such a way that they respond to overlapping regions in the visual field, which is widely used in image and video related tasks.

• Fine-Grained Image Analysis (FGIA) is a hot topic in computer vision and pattern recognition. The goals of FGIA are localizing the fine-grained objects, recognizing the objects’ subordinate categories, retrieving the fine-grained objects and so on.

• Long-Tailed Distribution Learning (LTDL) deals with real-world datasets displaying skewed distributions with a long tail, i.e., a few classes (a.k.a. head classes) occupy most of the data, while most classes (a.k.a. tail classes) have rarely few samples.

• General Object Detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class in digital images and videos.

• Weakly Supervised Learning (WSL), especially Multi-Instance Learning (MIL), is a variation on supervised learning. Instead of receiving a set of instances which are individually labeled, the learner receives a set of labeled bags, each containing many instances.

• Bag-of-Words Model (BoW) can be applied to image related tasks by encoding local visual descriptors of one image into a high dimensional vector. In BoW, there also include Vector of the Locally Aggregated Descriptors (VLAD) and Fisher Vector (FV).

Selected Publications

My papers are available for download in this Publications page, and here is my Google Scholar Citations profile.

• Fine-Grained Image Analysis with Deep Learning: A Survey.
  X.-S. Wei*, Y.-Z. Song, O. Mac Aodha, J. Wu, Y. Peng, J. Tang, J. Yang, and S. Belongie.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, 44(12): 8927-8948.

• A-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval. (Spotlight presentation)
  X.-S. Wei, Y. Shen, X. Sun, H.-J. Ye, and J. Yang.
  Neural Information Processing Systems (NeurIPS’21), Virtual, 2021, pp. 5720-5730.

• An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning. (Spotlight presentation)
  X.-S. Wei, H.-Y. Xu, F. Zhang, Y. Peng, and W. Zhou.
  Neural Information Processing Systems (NeurIPS’22), New Orleans, 2022, pp. xx-xx.

• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval.
  X.-S. Wei, J.-H. Luo, J. Wu, and Z.-H. Zhou.
  IEEE Transactions on Image Processing (TIP), 2017, 26(6): 2868-2881.

• Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories with Few Examples.
  X.-S. Wei, P. Wang, L. Liu, C. Shen, and J. Wu.
  IEEE Transactions on Image Processing (TIP), 2019, 28(12): 6116-6125.

• Multi-Instance Learning with Emerging Novel Class.
  X.-S. Wei, H.-J. Ye, X. Mu, J. Wu, C. Shen, and Z.-H. Zhou.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021, 33(5): 2109-2120.

• An Empirical Study on Image Bag Generators for Multi-Instance Learning.
  X.-S. Wei, and Z.-H. Zhou.
  Machine Learning, 2016, 105(2): 155-198.

• Prototype-based Classifier Learning for Long-Tailed Visual Recognition.
  X.-S. Wei, S.-L. Xu, H. Chen, L. Xiao, and Y. Peng.
  SCIENCE CHINA Information Sciences (中国科学：信息科学), 2022, 65(6): 160105.

• RPC: A Large-Scale and Fine-Grained Retail Product Checkout Dataset.
  X.-S. Wei*, Q. Cui, L. Yang, P. Wang, L. Liu, and J. Yang.
  SCIENCE CHINA Information Sciences (中国科学：信息科学), 2022, 65(9): 197101.

Professional Activities (Selected)

Young Scientists Committee

• Journal of Image and Graphics (中国图象图形学报), Nov. 2022 -

• Journal of Image and Graphics (中国图象图形学报), Dec. 2020 - Nov. 2022

Program Chair / Co-Chair

• Asian Conference on Computer Vision (ACCV) Workshop on Challenges of Fine-Grained Image Analysis, 2022

• ACM International Conference on Multimedia (ACM MM) Workshop on Multimedia Understanding with Less Labeling, 2021

• International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Long-Tailed Distribution Learning, 2021

• International Conference on Computer Vision (ICCV) Workshop on Understanding Social Behavior in Small Group Interactions, 2021

• Asian Conference on Computer Vision (ACCV) Workshop on Webly-Supervised Fine-Grained Recognition, 2020

Tutorial Chair

• ACCV 2022

Workshop Chair

• VALSE 2022

Publicity Chair

• PRCV 2020

Guest Editor

• Pattern Recognition Special Issue on Fine-Grained Object Retrieval, Matching and Ranking, 2021

• Journal of Computer Science & Technology Special Section on Self-Learning with Deep Neural Networks, 2021

Area Chair / Senior PC

• AAAI 2022

• IJCAI 2021, 2022

• ICME 2023

• BMVC 2021, 2022

Program Committee Member

• CVPR 2017, 2018, 2019, 2020, 2021, 2022, 2023

• ICCV 2017, 2019, 2021

• ECCV 2018, 2022

• NeurIPS 2016, 2018, 2020, 2021, 2022

• IJCAI 2018, 2019, 2020

• AAAI 2016, 2017, 2018, 2019, 2020, 2021, 2023

• ICLR 2021, 2022, 2023

• ICML 2022

• ACCV 2018, 2020

• BMVC 2019, 2020, 2021

• WACV 2021, 2023

• PRCV 2019, 2020, 2021

• …

Journal Reviewer

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

• International Journal of Computer Vision (IJCV)

• IEEE Transactions on Image Processing (TIP)

• Springer Journal of Machine Learning (MLJ)

• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

• IEEE Transactions on Multimedia (TMM)

• Elsevier Journal of Neural Networks (NN)

• Elsevier Journal of Pattern Recognition (PR)

• SCIENCE CHINA Information Sciences (中国科学：信息科学)

• 自动化学报

• 软件学报

• 电子学报

• 中国图象图形学报

• …

Correspondence

Mail

Xiu-Shen WEI
School of Computer Science and Engineering
Nanjing University of Science and Technology
Nanjing 210094, China

Office

Rm 4063-1, Building of Computer Science and Engineering, Xiaolingwei 200, Nanjing 210094, China

Tel

+86-025-8431-5017 (Ext Number: 8230/ 分机号: 8230)

(本网页ICP证：苏ICP备19033388号)