Liefeng Bo, Senior Research Scientist at Amazon

Amazon - Houston (SEA49)

224 Westlake Ave. N, Seattle, WA 98109

Email: liefengb at amazon dot com, liefengbo@gmail.com

Biography: On August 2013, I joined Amazon as a senior research scientist. I also hold an affiliate faculty in the Department of Computer Science and Engineering at the University of Washington (UW). My research interests are in Machine Learning, Computer Vision and Robotics. I was a senior research scientist at Intel Labs from 2012-2013 and a postdoc at the UW from 2010-2012 and at the Toyota Technological Institute at Chicago from 2008-2009. From 2002-2007, I was a PhD student at the Xidian University, where I received a doctorate in Electronic Engineering, with a specialization in Machine Learning.


[Research][Publication][Software][CV][Google Scholar Page]

News

  • We are hiring computer vision and machine learning scientists. Here are links to the positions. Contact us if you are interested.

  • Reproducible Research via Open Source Software and Open Access to Data and Publications

  • Multipath Sparse Coding Using Hierarchical Matching Pursuit: Source Code

  • Hierarchical Matching Pursuit for Learning Expressive Features from RGB-Detph Data: Source Code

  • Hierarchical Kernel Descriptors for RGB-Depth Data: Source Code, Dataset and Demos

  • Best Vision Paper Award at ICRA 2011 - Flagship Robotics Conference

  • 2010 National Excellent Doctoral Dissertation Award: Highest Award for PhD Thesis in China

Research Interests

  • Machine Learning: Deep Learning and Feature Learning, Hierarchical Matching Pursuit, Dictionary Learning and Sparse Coding, Big Data Systems, Support Vector Machines and Kernel Methods, Structured Prediction, Graphical Models

  • Computer Vision and Robotics: Object Recognition, Fine-Grained Recognition, Depth Cameras for Computer Vision, RGB-Depth Kernel Descriptors, Integrating Natural Language and Vision, Human Pose Estimation, Scene Understanding

Recent Software (More Software)

Recent Papers (More Papers)

Learning Hierarchical Sparse Representations [Software]

  • Liefeng Bo, Xiaofeng Ren and Dieter Fox, Learning Hierarchical Sparse Features for RGB-(D) Object Recognition, International Journal of Robotics Research (IJRR), 2014. [PDF] [BIB]

  • Kevin Lai, Liefeng Bo and Dieter Fox, Unsupervised Feature Learning for 3D Scene Labeling, In IEEE International Conference on Robotics and Automation (ICRA), May, 2014. [PDF] [BIB]

  • Marianna Madry, Liefeng Bo, Danica Kragic and Dieter Fox, ST-HMP: Unsupervised Spatio-Temporal Feature Learning for Tactile Data, In IEEE International Conference on Robotics and Automation (ICRA), May, 2014. [PDF] [BIB]

  • Michael Ruhnke, Liefeng Bo and Dieter Fox and Wolfram Burgard, Hierarchical Sparse Coded Surface Models, In IEEE International Conference on Robotics and Automation (ICRA), May, 2014. [PDF] [BIB]

  • Liefeng Bo, Xiaofeng Ren and Dieter Fox, Multipath Sparse Coding Using Hierarchical Matching Pursuit, In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2013. [PDF] [BIB] [Code]
    A new deep architecture for learning multi-layer sparse features; outperforms the state of the art object recognition algorithms by a large margin

  • Michael Ruhnke, Liefeng Bo and Dieter Fox and Wolfram Burgard, Compact RGBD Surface Models Based on Sparse Coding, In the AAAI Conference on Artificial Intelligence (AAAI), July 2013. [PDF] [BIB]
    Weighted KSVD for compressing 3D surface models

  • Xiaofeng Ren and Liefeng Bo, Discriminatively Trained Sparse Code Gradients for Contour Detection, Advances in Neural Information Processing Systems (NIPS), December, 2012. [PDF] [BIB] [Code]
    One-layer sparse coding features for contour detection; outperforms the popular gPb contour detector

  • Liefeng Bo, Xiaofeng Ren and Dieter Fox, Unsupervised Feature Learning for RGB-D Based Object Recognition, In International Symposium on Experimental Robotics, (ISER), June 2012. [PDF] [BIB] [Code] [Slides]
    Hierarchical matching pursuit (HMP) over four channels: grayscale, RGB, depth, and surfrace normal
    Higher accuracy than many state-of-the-art recognition algorithms

  • Liefeng Bo, Xiaofeng Ren and Dieter Fox, Hierarchical Matching Pursuit for Image Classification: Architecture and Fast Algorithms, Advances in Neural Information Processing Systems (NIPS), December, 2011. [PDF] [BIB] [Code] [Poster]
    A multi-layer sparse coding network that yields higher accuracy than single-layer sparse coding on top of SIFT
    Batch tree orthogonal matching pursuit for efficient sparse coding

Integrating Language and Vision

  • Yuyin Sun, Liefeng Bo and Dieter Fox, Learning to Identify New Objects, In IEEE International Conference on Robotics and Automation (ICRA), May, 2014. [PDF] [BIB]

  • Yuyin Sun, Liefeng Bo and Dieter Fox, Attribute Based Object Identification, In IEEE International Conference on Robotics and Automation (ICRA), May, 2013. [PDF] [BIB]
    Extract visual attributes from language descriptions and map them to the objects in RGB-D scenes

  • Cynthia Matuszek, Nicholas FitzGerald, Luke Zettlemoyer, Liefeng Bo, and Dieter Fox, A joint model of language and perception for grounded attribute learning, In International Conference on Machine Learning (ICML), July 2012. [PDF] [BIB]
    Joint learning of language and perception models for grounding attributes

RGB-D Kernel Descriptors [Software]

  • Shulin Yang, Liefeng Bo, Jue Wang and Linda Shapiro, Unsupervised Template Learning for Fine-Grained Object Recognition, Advances in Neural Information Processing Systems (NIPS), December, 2012. [PDF] [BIB]
    Kernel descriptors + unsupervised template learning for recognizing fine-grained object categories

  • Xiaofeng Ren, Liefeng Bo and Dieter Fox, RGB-(D) Scene Labeling: Features and Algorithms, In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2012. [PDF] [BIB] [Code]
    Kernel descriptors + segmentation tree achieves the state-of-the-art results on the NYU and Stanford Background datasets

  • Liefeng Bo, Xiaofeng Ren and Dieter Fox, Depth Kernel Descriptors for Object Recognition, In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2011. [PDF] [BIB] [Dataset] [Code]
    Kernel Descriptors over depth maps and 3D point clouds

  • Liefeng Bo, Kevin Lai, Xiaofeng Ren and Dieter Fox, Object Recognition with Hierarchical Kernel Descriptors, In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2011. [PDF] [BIB] [Dataset] [Code]
    Kernel descriptors over kernel descriptors: a deep architecture

  • Liefeng Bo, Xiaofeng Ren and Dieter Fox, Kernel Descriptors for Visual Recognition, Advances in Neural Information Processing Systems (NIPS), December, 2010. [PDF] [Spotlight] [Video] [BIB] [Code]
    A general approach to extract local features from pixel attributes that includes popular SIFT and HOG features as special cases

  • Liefeng Bo and Cristian Sminchisescu, Efficient Match Kernels between Sets of Features for Visual Recognition, Advances in Neural Information Processing Systems (NIPS), December, 2009. (spotlight acceptance rate 8%) [PDF][BIB]
    A kernel view of bag of words features leads to efficient match kernel families