Wenjia Xu (许文嘉)

Research Associate Professor, PhD Advisor

Beijing University of Posts and Telecommunications

Currently I am a research associate professor at School of Information and Communication Engineering, Beijing University of Posts and Telecommunications.

My research lies at the intersection of computer vision, natural language processing, and remote sensing, which covers a wide range of topics including remote sensing scene classification, few-shot learning, image captioning, explainable artificial inteligience.

I got my PhD degree from University of Chinese Academy of Sciences, advised by Prof. Yirong Wu. During my PhD, I'm also co-supervised by Prof. Zeynep Akata and Prof. Bernt Schiele at Max Plank Institute for Informatics. I got my Bachelar's degree with horner from Beijing Institute of Technology at 2016. During Jan.2016 - Jul.2016, I finished my bachelor thesis under the supervision of Prof. Tobias Oechtering at KTH.

I'm always looking for highly self-motivated PhD/master students, visiting students, and undergraduate interns (RAs) to work with me. Please directly send your CV to me (xuwenjia [AT] bupt.edu.cn) if you find my research interesting.

News

Selected Publications


Attribute Prototype Network for Any-Shot Learning

International Journal of Computer Vision, IJCV, 2022

Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata, [PDF, Project Page, Code].


Visually-Grounded Semantic Embeddings for Zero-Shot Learning

IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2022

Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata, [PDF, Project Page, Code].


On Distinctive Image Captioning via Comparing and Reweighting

IEEE Transactions on Pattern Analysis and Machine Intelligence, TPAMI, 2022

Jiuniu Wang*, Wenjia Xu*, Qingzhong Wang, Antoni B. Chan, (* = equal contribution) [PDF].


Human Attention in Fine-Grained Classification

British Machine Vision Conference, BMVC, 2021

Yao Rong, Wenjia Xu, Zeynep Akata, Enkelejda Kasneci, [PDF].


Group-based distinctive image captioning with memory attention

Proceedings of the 29th ACM International Conference on Multimedia, ACMMM, 2021

Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B. Chan, [PDF].


Attribute Prototype Network for Zero-Shot Learning

Neural Information Processing Systems, NeurIPS, 2020

Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata, [PDF, Project Page].


Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets

European Conference on Computer Vision, ECCV, 2020

Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B Chan, Oral, [PDF, Project Page].


Where is the Model Looking At --Concentrate and Explain the Network Attention

IEEE Journal of Selected Topics in Signal Processing, JSTSP, 2020

Wenjia Xu, Jiuniu Wang, Yang Wang, Guangluan Xu, Daoyu Lin, Wei Dai, Yirong Wu, [Link, PDF].


ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition

Knowledge-Based Systems, KBS, 2020

Jiuniu Wang, Wenjia Xu*, Xingyu Fu, Guangluan Xu, Yirong Wu, (* = corresponding author), [Link, PDF].


SRQA: Synthetic Reader for Factoid Question Answering

Knowledge-Based Systems, KBS, 2020

Jiuniu Wang, Wenjia Xu*, Xingyu Fu, Yang Wei, Li Jin, Ziyan Chen, Guangluan Xu, Yirong Wu, (* = corresponding author), [Link, PDF].


Deep Memory Connected Neural Network for Optical Remote Sensing Image Restoration

Remote Sensing

Wenjia Xu, Guangluan Xu, Yang Wang, Xian Sun, Daoyu Lin, Yirong Wu, [PDF, code].


SCRSR: An efficient recursive convolutional neural network for fast and accurate image super-resolution

Neurocomputing

Daoyu Lin, Guangluan Xu, Wenjia Xu, Yang Wang, Xian Sun, Kun Fu [Link&PDF].


High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network

IEEE International Symposium on Geoscience and Remote Sensing, IGARSS, 2018

Wenjia Xu, Guangluan Xu, Yang Wang, Xian Sun, Daoyu Lin, Wu Yirong, Oral ,[PDF].


For a full list, have a look at my Google Scholar page.

Services

Curriculum vitae