Kuiyuan YANG
Kuiyuan joined a self-driving startup since July 2017. Before that, he is a researcher at Microsoft Research Asia, and working on image content understanding for products such as Bing image search and XiaoIce. He received the Bachelor degree in Automation and Ph. D degree in Pattern Recognition and Intelligent Systems from University of Science and Technology of China, in 2007 and 2012, respectively.

Research Interests
  • Computer Vision
    • Object Recognition and Image Retrieval
  • Machine Learning
    • Deep Neural Network, Support Vector Machine

  • Startup
  • Researcher, Microsoft Research Asia, Sep.2015 ~Jun.2017.
  • Associate Researcher II, Microsoft Research Asia, Jul.2012 ~ Aug.2015.
  • Research Intern, Bing Multimedia Search, Microsoft Research Redmond, Mentored by Dr. Xian-Sheng Hua. Apr. 2012 ~ Jun. 2012.
  • Research Intern, Web Search & Mining Group, Microsoft Research Asia, Mentored by Dr. Lei Zhang. Dec. 2010 ~ Apr. 2012.
  • Research Intern, Multimedia Computing Group, Microsoft Research Asia,  Mentored by Dr. Xian-Sheng Hua.  Sep. 2008 ~ Dec. 2010.
  • Engineer Intern, Internet Media Group, Microsoft Research Asia, Mentored by Dr. Tao Mei. Jun. 2007 ~ Sep. 2007.


  • Yuhui Yuan, Kuiyuan Yang, Chao Zhang. Hard-Aware Deeply Cascaded Embedding. ICCV, 2017. [pdf]

  • Chuang Gan, Ting Yao, Kuiyuan Yang, Yi Yang, Tao Mei. You Lead, We Exceed: Labor-free Video Concept Learning by Jointly Exploiting Web Videos and Images. CVPR, 2016.
  • Guotian Xie, Kuiyuan Yang, Yalong Bai, Min Shang, Yong Rui, Jianhuang Lai. Improve Dog Recognition By Mining More Information From Both Click-through Logs and Pre-trained Models. IEEE International Conference on Multimedia &Expo Workshops, 2016.[pdf][dataset] (rank 1st in the track of without using extra data and 2nd in all teams)

  • Yalong Bai, Kuiyuan Yang, Wei Yu, Chang Xu, Wei-Ying Ma, Tiejun Zhao. Automatic Image Dataset Construction from Click-through Logs Using Deep Neural Network. ACM Multimedia, 2015. [pdf]

  • Wei Yu, Kuiyuan Yang, Yalong Bai, Hongxun Yao, Yong Rui. Learning Cross Space Mapping via DNN using Large Scale Click-through Logs. IEEE Transactions on Multimedia, 2015.

  • Xinmei Tian, Zhe Dong, Kuiyuan Yang, Tao Mei. Query-dependent Aesthetic Model with Deep Learning for Photo Quality Assessment. IEEE Transactions on Multimedia, 2015.

  • Yijie Lu, Linjun Yang, Kuiyuan Yang, Yong Rui. Mining Latent Attributes from Click-through Logs for Image Recognition. IEEE Transactions on Multimedia, 2015.

  • Zheng Xu, Xue Li, Kuiyuan Yang, Tom Goldstein. Exploiting Low-rank Structure for Discriminative Sub-categorization. BMVC, 2015.

  • Wei Yu, Kuiyuan Yang, Yalong Bai, Hongxun Yao, Yong Rui. Visualizing and Comparing Convolutional Neural Networks. [pdf][code]

  • Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, Zheng Zhang. The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification. CVPR, 2015. [pdf]

  • Jianlong Fu, Tao Mei, Kuiyuan Yang, Hanqing Lu, Yong Rui. Tagging Personal Photos with Transfer Deep Learning. WWW, 2015.

  • Tianjun Xiao, Jiaxing Zhang, Kuiyuan Yang, Yuxin Peng, Zheng Zhang. Error-driven incremental learning in deep convolutional neural network for large-scale image classification. ACM Multimedia, 2014. [pdf]

  • Jiajun Wang, Yu-Gang Jiang, Qiang Wang, Kuiyuan Yang, Chong-Wah Ngo. Organizing Video Search Results to Adapted Semantic Hierarchies for Topic-based Browsing. ACM Multimedia, 2014. (Best Poster Award)

  • Yalong Bai, Wei Yu, Tianjun Xiao, Chang Xu, Kuiyuan Yang, Wei-Ying Ma, Tiejun Zhao. Bag-of-Words Based Deep Neural Network for Image Retrieval. ACM Multimedia, 2014. (won the 1st place)

  • Wei Yu, Kuiyuan Yang, Yalong Bai, Hongxun Yao, Yong Rui. DNN Flow: DNN feature pyramid based image matching. BMVC, 2014. [pdf]

  • Yalong Bai, Kuiyuan Yang, Wei Yu, Wei-Ying Ma, Tiejun Zhao. Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data. ICLR, 2013.

  • Pengfei Xu, Lei Zhang, Kuiyuan Yang, Hongxun Yao. Nested-SIFT for Efficient Image Matching and Retrieval. IEEE Multimedia, 2013.

  • Wei Yu, Hongxun Yao, Kuiyuan Yang, Lei Zhang. The shortest warping path based multiple images alignment. ICIP, 2013.

  • Yingwei Pan, Ting Yao, Kuiyuan Yang, Houqiang Li, Chong-Wah Ngo, Jingdong Wang, Tao Mei. Image search by graph-based label propagation with image representation from DNN. ACM Multimedia, 2013.

  • Kuiyuan Yang, Lei Zhang, Yong Rui, Hong-Jiang Zhang. PartBook for Image Parsing. The Eighth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision, 2012. [pdf]

  • Kuiyuan Yang, Lei Zhang, Meng Wang, Hong-Jiang Zhang. Semantic Point DetectorACM Multimedia, 2011. [pdf]

  • Kuiyuan Yang, Meng Wang, Xian-Sheng Hua, Shuicheng Yan, Hong-Jiang Zhang. Assemble New Object Detector with Few Examples. IEEE Transactions on Image Processing, 2011. [pdf]

  • Kuiyuan Yang, Xian-Sheng Hua, Meng Wang, Hong-Jiang Zhang. Tag Tagging: Towards More Descriptive Keywords of Image Content. IEEE Transactions on Multimedia, 2011. [pdf]

  • Meng Wang, Kuiyuan Yang, Xian-Sheng Hua, Hong-Jiang Zhang. Towards Relevant and Diverse Search of Social Images. IEEE Transactions on Multimedia, 2010. [pdf]

  • Kuiyuan Yang, Meng Wang, Xian-Sheng Hua, Hong-Jiang Zhang. Social Image Search with Diverse Relevance Ranking. International Conference on MultiMedia Modeling, 2010. (Best Paper Award) [pdf]

  • Kuiyuan Yang, Xian-Sheng Hua, Meng Wang, Hong-Jiang Zhang. Tagging TagsACM Multimedia, 2010. [pdf]

  • Meng Wang, Kuiyuan Yang, Xian-Sheng Hua, Hong-Jiang Zhang. Visual Tag Dictionary: Interpreting Tags with Visual Words. Proceedings of the 1st workshop on Web-scale multimedia corpus, 2009. [pdf]

  • Kuiyuan Yang, Meng Wang, Hong-Jiang Zhang. Active Tagging for Image Indexing. International Conference on Multimedia and Expo, 2009. [pdf]

  • Gong Chen, Kuiyuan Yang, Heqin Zhou, Jiefeng Yan. A Robust System for Real-time Multiple-Vehicle Detection and Tracking. Signal Processing, 2009. (in Chinese) [pdf]

[back to top]