Full name: Tam Le 
(Vietnamese name: Lê Thanh Tâm)
Postdoctoral Researcher
High-Dimensional Statistical Unit, Generic Technology Research Group
RIKEN Center for Advanced Intelligence Project (RIKEN AIP)
Email: tam.le(AT)riken.jp    or    lttam.vn(AT)gmail.com
My CV is here [PDF]. (Updated in April, 2017)

*** News ***

  • 01-Sep-2017, Join in High-Dimensional Statistical Unit, RIKEN AIP as a postdoctoral researcher.
  • 05-Apr-2017, Our proposal has been accepted by the Grants-in-Aid for Young Scientists (B) as PI (04/2017 - 03/2020).

Research Support

  • 04/2017 - 03/2020, JSPS grant (Grants-in-Aid for Young Scientists (B) as PI).

    Education

    Research Experiences

    Publication

    • Journals
      • Tam Le, Marco Cuturi, Adaptive Euclidean Maps for Histograms: Generalized Aitchison Embeddings, Machine Learning Journal (MLJ), 2014. [Springer/PDF/PROJECT/Bibtex]
      • Tam Le, Yousun Kang, Akihiro Sugimoto, Image Categorization Using Hierarchical Spatial Matching Kernel, Journal of the Institute of Image Electronics Engineers of Japan (IIEEJ), Vol. 42, No. 2, 2013. [PDF/PROJECT/Bibtex]
    • Conference papers
      • Tam Le, Geometry-Aware Learning Algorithms for Histogram Data Using Adaptive Metric Embeddings and Kernel Functions, PhD thesis, Kyoto University, Japan, 2015. [PDF]
      • Tam Le, Marco Cuturi, Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations, International Conference on Machine Learning (ICML), France, 2015. [VideoLecture/PDF/Supplementary/Full-PDF/SLIDE/POSTER/Bibtex(Acceptance rate: 270/1037 = 26%)
      • Tam Le, Marco Cuturi, Generalized Aitchison Embeddings for Histograms, The 5th Asian Conference on Machine Learning (ACML), JMLR vol.29, Australia, 2013 (oral). [PDF/SLIDE/PROJECT/Bibtex] (Acceptance rate: 31%, oral paper rate: 9.7%)
      • Tam Le, Yousun Kang, Akihiro Sugimoto, Son Tran, Thuc Nguyen, Hierarchical Spatial Matching Kernel for Image Categorization, International Conference on Image Processing and Recognition (ICIAR), LNCS 6753, Canada, 2011 (oral). [PDF/SLIDE/PROJECT/Bibtex] (Acceptance rate: 57%, oral paper rate: 25%)
      • Tam Le, Son Tran, Seichii Mita, Thuc Nguyen, Realtime Traffic Sign Detection Using Color and Shape-Based Features, The 2nd Asian Conference on Intelligent Information and Database Systems (ACIIDS), LNAI 5991, Vietnam, 2010 (oral). [PDF/SLIDE/PROJECT/Bibtex]

    Talks

    • 2016, Geometry-Aware Metric Learning for Histograms, MI2I Open Seminar Series at National Institute for Materials Science (NIMS), Japan. [SLIDE]
    • 2015, Geometry-Aware Learning Algorithms for Histogram Data Using Adaptive Metric Embeddings and Kernel Functions, PhD defense, Graduate School of Informatics, Kyoto University, Japan.
    • 2015, Metric Learning for Histograms, Nagoya Institute of Technology, Japan.
    • 2015, Unsupervised Riemannian Metric Learning for Histograms, Bioinformatics Center, Institute for Chemical Research, Kyoto University, Japan.
    • 2015, Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations, IST Seminar, Graduate School of Informatics, Kyoto University, Japan. [SLIDE]
    • 2014, Adaptive Euclidean Maps for Histograms: Generalized Aitchison Embeddings, Progress Meeting Report for PhD program, Graduate School of Informatics, Kyoto University, Japan. [SLIDE]
    • 2014,  Adaptive Euclidean Maps for Histograms: Generalized Aitchison Embeddings, Lear, INRIA Rhone-Alpes, Grenoble, France. [SLIDE]

    Awards

    Professional Services

    Special Courses & TA

    Code & Dataset

    • Generalized Aitchison Embeddings [More detail].
    • Hierarchical Spatial Matching Kernel - HSMK (CALTECH-101) - NII 2011 [More detail].
    • C++ code for Traffic Sign Detection project - TTI 2009 [More detail].
    • Color Training Dataset for Traffic Sign Segmentation [More detail].
    • Test Dataset for Traffic Sign Detection [More detail].

    Research Interests: Machine Learning & Computer Vision