Wei Zhang

I am a Research Director at SenseTime Group Limited. I also serve as an EXCO member of AI Specialist Group of Hong Kong Computer Society. Before I was a quantitative trader, developing market-making strategies with the knowledge of machine learning and market microstructure. I was a participant on the predictive modelling competition platform Kaggle. My highest Kaggle ranking was 6th. I obtained the PhD degree from The Chinese University of Hong Kong, and the BEng degree from Tsinghua University, Beijing. I spent a year as a research intern at Microsoft Research Asia. I published 19 papers on top journals such as TPAMI, TMM, TKDE and conferences such as CVPR, IJCAI, MM. I am also a reviewer of a few journals, including IJCV, TPAMI, TIP, TNNLS and TIFS. Email: We have openings for research interns in the field of scalable deep learning, video understanding and reinforcement learning. Please contact me via email.

Selected Research (Publication List, Projects)

• Video action recognition

  • Temporal sequence distillation: Towards few-frame action recognition in videos
    ACM MM 2018

  • Optical flow guided feature: A fast and robust motion representation for video action recognition
    CVPR 2018

• Video summarization

  • Extractive video summarizer with memory augmented neural networks
    ACM MM 2018

• Fast text detection

  • Boosting up scene text detectors with guided CNN
    Oral presentation, BMVC 2018

• Clustering

  • Graph degree linkage: Agglomerative clustering on a directed graph
    ECCV 2012 matlabcentral github

• Cross-modality face recognition

  • Coupled information-theoretic encoding for face photo-sketch recognition
    Oral presentation, CVPR 2011 video
    
    
    
    
    
    

Copyright © 2017 Wei Zhang.