Wenjie Pei (裴文杰)

Contact

Email: wenjiecoder@outlook.com; wenjiecoder@gmail.com

Homepage: https://wenjiepei.github.io

Address: Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen.

Biography

Wenjie Pei is an Assistant Professor with the Harbin Institute of Technology, Shenzhen, China.

He got his Ph.D. at Pattern Recognition and Computer Vision Lab, Delft University of Technology and worked with Dr. Laurens van der Maaten (Facebook AI Research) and Prof. David Tax (TU Delft). Before joining Harbin Institute of Technology, he was a Senior Researcher on Computer Vision at Tencent Youtu X-Lab. In 2016, he was a visiting scholar with the Carnegie Mellon University (CMU). His research interests lie in Computer Vision and Pattern Recognition.

Please visit my homepage for details: https://wenjiepei.github.io.

Collaborations: I am always looking for highly self-motivated students, including undergraduate, graduate and PhD students, for research collaborations on Computer Vision and Machine Learning. Feel free to contact me with your CV.

Education Background

• 10/2013 - 6/2018:  Ph.D. in Pattern Recognition and Computer Vision Lab, Delft University of Technology (TU Delft), the Netherlands.
  Supervisors: Prof. David Tax and Dr. Laurens van der Maaten (Facebook AI Research).

• 08/2011 - 08/2013: M.Sc. of Computer Science and Engineering, Eindhoven University of Technology (TU/e), the Netherlands.
  Supervisor: Prof. Toon Calders.

• 09/2008 - 03/2011: M.Sc. of Computer Science and Technology in State Key Lab of CAD&CG, ZheJiang University (ZJU), China.
  Supervisors: Prof. Jin Huang and Prof. Hujun Bao.

• 09/2004 - 06/2008: B.Sc. in Shanghai JiaoTong University (SJTU), China.
  B.Sc. of Computer Science and Engineering.
  B.Sc. of Business Administration.

Experience

• 07/2018 - 12/2019, Tencent Youtu X-Lab.
  Senior Researcher in Computer Vision.

• 07/2016 - 12/2016, Carnegie Mellon University (CMU).
  Visiting Scholar in Language Technology Institute (LTI).
  Supervisors: Prof. Louis-Philippe Morency and Dr. Tadas Baltrušaitis.

• 03/2013 - 08/2013, Intern at Philips Research Eindhoven.

Research Interests

• Sequence modeling

• Deep Learning

• Image/video synthesis

• Image/video captioning

• Semantic/instance segmentation

• Person ReID, Face recognition

• Network pruning

• Image synthesis

• Tracking

Publications

• Yi Li, Wenjie Pei*, Zhenyu He*. (* joint corresponding author). SRHEN: Stepwise-Refining Homography Estimation Network via Parsing Geometric Correspondence in Deep Latent Space. ACM MM, 2020. (计算机多媒体顶会，CCF A类)

• Qi Fan, Lei Ke, Wenjie Pei*, Chi-Keung Tang and Yu-Wing Tai. (*Corresponding author). Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation. ECCV, 2020. (计算机视觉顶会)

• Jiadong Liang^#, Wenjie Pei^# and Feng Lu. (^#Equal contribution). CPGAN: Content-Parsing Generative Adersarial Networks for Text-to-Image Synthesis. ECCV, Spotlight (5% acceptance rate), 2020. (计算机视觉顶会). This work is conducted by Jiadong (phd student from BeiHang University) under my supervision.

• Wenjie Pei, Hamdi Dibeklioğlu, Tadas Baltrušaitis and David M.J. Tax. Attended End-to-end Architecture for Age Estimation from Facial Expression Videos. Transactions on Image Processing (TIP) (Impact Factor: 9.34), 2020. (CCF A类，中科院一区)

• Canmiao Fu^#, WenjiePei^#, Qiong Cao, Chaopeng Zhang, Xiaoyong Shen, Yong Zhao and Yu-wing Tai (^#Equal contribution). Non-local Recurrent Neural Memory for Supervised Sequence Modeling. International Conference on Computer Vision (ICCV) Oral (4.3% acceptance rate), 2019. (CCF A类)

• Lei Ke, Wenjie Pei, Ruiyu Li, Xiaoyong Shen and Yu-wing Tai. Reflective Decoding Network for Image Captioning. International Conference on Computer Vision (ICCV), 2019. This work is conducted by my intern Lei Ke under my supervision. (CCF A类)

• Yunqiang Li^#, Wenjie Pei^#, Yufei Zha and Jan van Gemert (^#Equal contribution). Push for Quantization: Deep Fisher Hashing. BMVC Oral (4.7% acceptance rate), 2019.  

• Wenjie Pei, Jiyuan Zhang, Xiangrong Wang, Lei Ke, Xiaoyong Shen and Yu-wing Tai. Memory-Attended Recurrent Network for Video Captioning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (CCF A类)

• Weinong Wang, Wenjie Pei*, Qiong Cao, Shu Liu and Yu-wing Tai (*corresponding authors). Orthogonal Center Learning with Subspace Masking for Person Re-identification. arXiv, 2019.

• Wenjie Pei, Hamdi Dibeklioğlu, David MJ Tax and Laurens van der Maaten. Multivariate Time Series Classification using the Hidden-Unit Logistic Model. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (Impact Factor: 8.79), 2018. (中科院一区)

• Wenjie Pei, David M.J. Tax. Unsupervised Learning of Sequence Representations by Autoencoder. arXiv, 2018.

• Wenjie Pei^#, Jie Yang^#, Zhu Sun, Jie Zhang, Alessandro Bozzon and David MJ Tax (^#Equal contribution). Interacting Attention-gated Recurrent Networks for Recommendation. ACM International Conference on Information and Knowledge Management (CIKM), full paper, 2017. (CCF B类)

• Wenjie Pei, Tadas Baltrušaitis, David M.J. Tax and Louis-Philippe Morency. Temporal Attentijon-Gated Model for Robust Sequence Classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. (CCF A类)

• Wenjie Pei, David M.J. Tax and Laurens van der Maaten. Modeling Time Series Similarity with Siamese Recurrent Networks. arXiv, 2016.

• Hoang Thanh Lam, Wenjie Pei, Adriana Prado, Baptiste Jeudy, Élisa Fromont, Toon Calders. Mining Top-K Largest Tiles in a Data Stream. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2014. (CCF B类)

• Jin Huang, Wenjie Pei, Chunfeng Wen, Guoning Chen, Wei Chen, Hujun Bao. Output-Coherent Image-Space LIC for Surface Flow Visualization. IEEE Pacific Visualization (PacificVis), full paper, 2012.

• Jin Huang, Muyang Zhang, Wenjie Pei, Hujun Bao. Controllable Highly Regular Triangulation, SCIENCE CHINA-Information Sciences (Impact Factor: 3.30), 2011. （中科院二区）