Dr. Dayong Wang


Dr. Wang worked as a Research Fellow in NTU-UBC Research Center of Excellence in Active Living for the Elderly, as a Postdoctoral Researcher under the supervision of Distinguished Professor Anil Jain, who is a member of the National Academy of Engineering, in the Department of Computer Science & Engineering at Michigan State University, and as a Research Fellow at Harvard Medical School under the supervision of Prof. Andrew Beck, who was also the Director of Bioinformatics at the Cancer Research Institute of Beth Israel Deaconess Medical Center (BIDMC). Since 2017, Dr. Wang has been Vice President of Machine Learning in PathAI.

Dr. Wang received his B.S. from the Department of Computer Science and Technology at Tsinghua University in 2008, and his Ph.D. from the School of Computer Science and Engineering (SCSE) at Nanyang Technological University in 2014, under the supervision of Prof. Steven C.H. Hoi and Prof. Ying He. His research interests are deep learning, artifical intelligence, machine learning, computer vision, and computational pathology

Stay hungry. Stay foolish. -- Steven Jobs 1955-2011

Publications and Talks [Full List]


  1. Manan Shah, Christopher Rubadue, David Suster, and Dayong Wang,
    Deep Learning Assessment of Tumor Proliferation in Breast Cancer Histological Images,
    arXiv:1610.03467pdf ][ link ]
  2. Dayong Wang, Aditya Khosla, Rishab Gargeya, Humayun Irshad, and Andrew Beck,
    Deep Learning for Identifying Metastatic Breast Cancer,
    arXiv:1606.05718pdf ][ link ]
  3. Dayong Wang, Pengcheng Wu, Peilin Zhao, Steven C.H. Hoi,
    A Framework of Sparse Online Learning and Its Applications,
    arXiv:1507.07146pdf ][ link ]
  4. Dayong Wang, Charles Otto, Anil K. Jain,
    Face Search at Scale: 80 Million Gallery,
    arXiv:1507.07242pdf ][ link ]


  1. Charles, Otto, Dayong Wang, and Anil K. Jain,
    Clustering Millions of Faces by Identity,
    Pattern Analysis and Machine Intelligence, IEEE Transactions on (TPAMI), Vol. xx, No. x, p.xx–xx, March, 2017.
    pdf ][ link ]
  2. Dayong Wang, Charles, Otto, and Anil K. Jain,
    Face Search at Scale,
    Pattern Analysis and Machine Intelligence, IEEE Transactions on (TPAMI), Vol. 39, No. 3, p.1122–1136, June, 2016.
    pdf ][ link ]
  3. Dayong Wang, Hoi, S.C.H., Ying He, Jianke Zhu, Tao Mei and Jiebo Luo,
    Retrieval-Based Face Annotation by Weak Label Regularized Local Coordinate Coding,
    Pattern Analysis and Machine Intelligence, IEEE Transactions on (TPAMI), Vol. 36, No. 3, p.550–563, March, 2014.
    pdf ][ link ]
  4. Dayong Wang, Hoi, S.C.H., Ying He and Jianke Zhu,
    Mining Weakly Labeled Web Facial Images for Search-Based Face Annotation,
    Knowledge and Data Engineering, IEEE Transactions on (TKDE), Vol. 26, No. 1, p.166–179, Jan, 2014.
    pdf ][ link ]
  5. Boon-Seng Chew, Chau, L-P, Ying He, Dayong Wang and Hoi, S.C.H.,
    Spectral Geometry Image: Image Based 3D Models for Digital Broadcasting Applications,
    Broadcasting, IEEE Transactions on, Vol. 57, No. 3, p.636–645, 2011.
    link ]

Conferences and Workshops

  1. Dayong, Wang, Anil K. Jain,
    Face Retriever: Pre-filtering the Gallery via Deep Neural Net,
    International Conference on Biometrics (ICB2015) , 2015.
    pdf ][ link ]
  2. Ji, Wan, Pengcheng, Wu, Steven, C. H., Hoi, Peilin, Zhao, Dayong, Wang,
    Online Learning to Rank for Content-Based Image Retrieval,
    24th International Joint Conference on Artificial Intelligence (IJCAI-15) , 2015.
    link ]
  3. Dayong, Wang, Pengcheng, Wu, Peilin, Zhao, Chunyan, Miao, and Steven C.H., Hoi,
    High-dimensional Data Stream Classification via Sparse Online Learning,
    IEEE International Conference on Data Mining (ICDM2014), 2014.
    pdf ][ link ]
  4. Ji, Wan, Dayong, Wang, Steven C.H. , Hoi, Pengcheng, Wu, Jianke, Zhang and Jintao, Li,
    Deep Learning for Content-Based Image Retrieval: A Comprehensive Study,
    Proceedings of the ACM International Conference on Multimedia (MM) , 2014.
    pdf ][ link ]
  5. Wang, Dayong, Hoi, Steven C.H., Wu, Pengcheng, Zhu, Jianke, He, Ying and Miao, Chunyan,
    Learning to Name Faces: A Multimodal Learning Scheme for Search-based Face Annotation,
    Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, p.443–452, 2013.
    pdf ][ link ]
  6. Pengcheng, Wu, Steven, C.H., Hoi, Hao, Xia, Peilin, Zhao, Dayong, Wang, Chunyan, Miao,
    Online Multimodal Deep Similarity Learning with Application to Image Retrieval,
    The 21st ACM International Conference on Multimedia, 2013.
    pdf ][ link ]
  7. Hoi, Steven C.H., Wang, Dayong, Cheng, I. Yeu, Lin, Elmer Weijie, Zhu, Jianke, He, Ying and Miao, Chunyan,
    FANS: face annotation by searching large-scale web facial images,
    Proceedings of the 22nd international conference on World Wide Web companion, p.317–320, 2013.
    pdf ][ link ]
  8. Wang, Dayong, Hoi, Steven Chu Hong and He, Ying,
    A Unified Learning Framework for Auto Face Annotation by Mining Web Facial Images,
    Proceedings of the 21st ACM International Conference on Information and Knowledge Management, p.1392–1401, 2012.
    pdf ][ link ]
  9. Wang, Dayong, Hoi, Steven C.H., He, Ying and Zhu, Jianke,
    Retrieval-based Face Annotation by Weak Label Regularized Local Coordinate Coding,
    Proceedings of the 19th ACM International Conference on Multimedia, p.353–362, 2011.
    pdf ][ link ]
  10. Wang, Dayong, Hoi, Steven C.H. and He, Ying,
    Mining Weakly Labeled Web Facial Images for Search-based Face Annotation,
    Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, p.535–544, 2011.
    pdf ][ link ]
  11. Wang, Dayong, Hoi, Steven C. H. and 0001, Ying He,
    An Effective Approach to Pose Invariant 3D Face Recognition.,
    MMM (1), Vol. 6523, p.217–228, 2011.
    link ]
  12. He, Ying, Chew, Boon-Seng, Wang, Dayong, Hoi, Chu-Hong and Chau, Lap-Pui,
    Streaming 3D meshes using spectral geometry images,
    Proceedings of the 17th ACM international conference on Multimedia, p.431–440, 2009.
    link ]

Awards & Scholarship

♣ No.1 at 2016 ISBI challenge on cancer metastasis detection in lymph node

From October 2015 to April 2016, the International Symposium on Biomedical Imaging (ISBI) held the Camelyon Grand Challenge 2016 (Camelyon16) to identify topperforming computational image analysis systems for the task of automatically detecting metastatic breast cancer in digital whole slide images (WSIs) of sentinel lymph node biopsies. Camelyon16 was a highly successful challenge with 32 submissions from as many as 23 teams. We achieved the best performance on both evaluaton metrics.

♣ 2013年度国家优秀自费留学生奖学金

Given by the China Scholarship Council, this award is presented to 500 students worldwide, with only a distinguished five selected as the Extra-Outstanding Award winners.

♣ Research Scholarship, Nanyang Technological University, 2009-2013

♣ Scholarships, Tsinghua University, 2004-2008


Deep Learning for Identifying Metastatic Breast Cancer (Presentation) (Details)

The International Symposium on Biomedical Imaging (ISBI) held a grand challenge to evaluate computational systems for the automated detection of metastatic breast cancer in whole slide images of sentinel lymph node biopsies. Our team won both competitions in the grand challenge, obtaining an area under the receiver operating curve (AUC) of 0.925 for the task of whole slide image classification and a score of 0.7051 for the tumor localization task. A pathologist independently reviewed the same images, obtaining a whole slide image classification AUC of 0.966 and a tumor localization score of 0.733. Combining our deep learning system’s predictions with the human pathologist’s diagnoses increased the pathologist’s AUC to 0.995, representing an approximately 85 percent reduction in human error rate. These results demonstrate the power of using deep learning to produce significant improvements in the accuracy of pathological diagnoses

Large-scale Face Retrieval (Visualization) (Details)

We propose a face search system which combines a fast search procedure, coupled with a state-of-the-art commercial off the shelf (COTS) matcher, in a cascaded framework. We evaluate the proposed face search system on a gallery containing 80 million web-downloaded face images. Experimental results demonstrate that the deep features are competitive with state-of-the-art methods on unconstrained face recognition benchmarks. Further, the proposed face search system offers an excellent trade-off between accuracy and scalability on datasets consisting of millions of images. Additionally, in an experiment involving searching for face images of the Tsarnaev brothers, convicted of the Boston Marathon bombing, the proposed cascade face search system could find the younger brother's (Dzhokhar Tsarnaev) photo at rank 1 on a 5M gallery and at rank 8 on an 80M gallery.

Search-based Face Annotation (video) (Details)

Auto face annotation is an important technique for online photo album management, new video summarization, and so on. It aims to automatically detect human faces from a photo image and further name the faces with the corresponding human names. Our demo system was built upon a large-scale real-world web facial image database with a total of 6,025 persons and about 1 million facial images. This paper demonstrates the potential of searching and mining web-scale weakly labeled facial images on the internet to tackle the challenging face annotation problem, and addresses some open problems for future exploration by researchers in web community.

Codes & Data

Weakly Labeled Faces on the web (WLFDB) (Details)