Tian Lan


Research Scientist
Amazon Go

E-mail: tianlan@amazon.com

 

 

  • We have just launched Amazon Go, a new kind of store with no lines and no checkout! We created the "just walk out" experience using computer vision and machine learning to automatically figure out "who" takes "what" product and therefore completely eliminate the need for checkout!
  • In September 2014, I joined Amazon as a research scientist.
  • I am co-organizing the 1st Workshop on Understanding Human Activities: Context and Interactions, which is to be held in conjunction with ICCV 2013, along with Sameh Khamis, Mohamed Amer, and Wongun Choi.

  • SHORT BIO [CV]

    Tian Lan is a research scientist at Amazon. Prior to joining Amazon, he was a post-doctoral researcher at Stanford University, working with Prof. Silvio Savarese. He received his Ph.D. in Computer Science from Simon Fraser University in 2013 under the supervision of Prof. Greg Mori. He earned his M.Sc. also from Simon Fraser, in 2010, and his B.Eng. from Huazhong University of Science and Technology, China in 2008. He spent his 2011 summer and 2012 fall as an intern at Disney Research Pittsburgh, where he worked with Dr. Leonid Sigal on sports video understanding and object detection. His Ph.D. thesis on structured visual recognition won the CIPPRS Doctoral Dissertation Award, awarded annually to the top thesis in Canada in the field of computer vision and robotics.


    RESEARCH INTERESTS

    My research interests are in computer vision and machine learning, and include human activity recognition, object recognition and image retrieval. The focus of my research is on developing rich structured representations (e.g. activity hierarchies, structured object queries) and learning algorithms for semantic understanding of visual scenes from static images as well as video sequences. Here is a wordle generated from the titles of my papers.

    PUBLICATIONS

    2015

    Tian Lan*, Yuke Zhu*, Amir R. Zamir, and Silvio Savarese

    Action Recognition by Hierarchical Mid-level Action Elements

    International Conference on Computer Vision (ICCV), 2015

    [pdf] [bibtex] [project]

    2014

    Tian Lan, Tsung-Chuan Chen, and Silvio Savarese

    A Hierarchical Representation for Future Action Prediction

    European Conference on Computer Vision (ECCV), 2014

    [pdf] [bibtex] [project]

    Tian Lan, Lei Chen, Zhiwei Deng, Guang-Tong Zhou, and Greg Mori

    Learning Action Primitives for Multi-Level Video Event Understanding

    International Workshop on Visual Surveillance and Re-Identification (at ECCV), 2014

    [pdf] [bibtex]

    2013

    Guang-Tong Zhou, Tian Lan, Arash Vahdat, and Greg Mori

    Latent Maximum Margin Clustering

    Neural Information Processing Systems (NIPS), 2013

    [pdf] [bibtex]

    Tian Lan, Michalis Raptis, Leonid Sigal, and Greg Mori

    From Subcategories to Visual Composites: A Multi-Level Framework for Object Detection

    IEEE International Conference on Computer Vision (ICCV), 2013

    [pdf] [bibtex]

    Tian Lan and Greg Mori

    A Max-Margin Riffled Independence Model for Image Tag Ranking

    IEEE Computer Vision and Pattern Recognition (CVPR), 2013

    [pdf] [bibtex]

    Guang-Tong Zhou, Tian Lan, Weilong Yang, and Greg Mori

    Learning Class-to-Image Distance with Object Matchings

    IEEE Computer Vision and Pattern Recognition (CVPR), 2013

    [pdf] [bibtex]

    Yuke Zhu, Tian Lan, Yijian Yang, Steven Robinovitch, and Greg Mori

    Latent Spatio-temporal Models for Action Localization and Recognition in Surveillance Video

    IAPR International Conference on Machine Vision Applications (MVA), 2013 (oral)

    [pdf] [bibtex]

    2012

    Mani Ranjbar, Tian Lan, Yang Wang, Stephen Robinovitch and Greg Mori

    Optimizing Non-Decomposable Loss Functions in Structured Prediction

    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2012

    [pdf] [bibtex]

    Tian Lan, Weilong Yang, Yang Wang, and Greg Mori

    Image Retrieval with Structured Object Queries Using Latent Ranking SVM

    European Conference on Computer Vision (ECCV), 2012

    [pdf] [bibtex] [data]

    Nataliya Shapovalova, Arash Vahdat, Kevin Cannons, Tian Lan, and Greg Mori

    Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification

    European Conference on Computer Vision (ECCV) , 2012

    [pdf] [bibtex]

    Tian Lan, Leonid Sigal, and Greg Mori

    Social Roles in Hierarchical Models for Human Activity Recognition

    IEEE Computer Vision and Pattern Recognition (CVPR), 2012

    [pdf] [bibtex]

    Tian Lan, Yang Wang, Weilong Yang, Stephen Robinovitch, and Greg Mori

    Discriminative Latent Models for Recognizing Contextual Group Activities

    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2012

    [pdf] [bibtex]

    2011

    Tian Lan, Yang Wang, and Greg Mori

    Discriminative Figure-Centric Models for Joint Action Localization and Recognition

    IEEE International Conference on Computer Vision (ICCV), 2011

    [pdf] [bibtex] [training-testing split]

    2010

    Tian Lan, Yang Wang, Weilong Yang, and Greg Mori

    Beyond Actions: Discriminative Models for Contextual Group Activities

    Neural Information Processing Systems (NIPS), 2010

    [pdf] [bibtex] [project] [poster]

    Tian Lan, Yang Wang, Greg Mori, and Stephen Robinovitch

    Retrieving Actions in Group Contexts

    International Workshop on Sign Gesture Activity (at ECCV), 2010

    [pdf] [bibtex]

    2009 & before
    trecvid

    Weilong Yang, Tian Lan, and Greg Mori

    SFU at TRECVid 2009: Event Detection

    TRECVID Workshop , 2009

    [pdf] [project]

    Tian Lan, Yangguang Sun, and Mingyue Ding

    A fast quantum mechanics based contour extraction algorithm

    SPIE Medical Imaging: Image Processing, 2009.

    Yangguang Sun, Tian Lan, Xiaowei Fu, and Mingyue Ding

    A statistical approach to contour extraction based on quantum mechanics

    SPIE Medical Imaging: Image Processing, 2009.

    Tian Lan and Jinlin Zhang

    FPGA Implementation of an Adaptive Noise Canceller

    International Symposium on Information Processing (ISIP), 2008.


    Ph.D. Thesis

    Tian Lan

    From Flat to Hierarchical: Modeling Structures in Visual Recognition

    Phd thesis, Simon Fraser University, August 2013

    [pdf] [slides]