Bangpeng Yao (姚邦鹏)

Short Bio     [Full CV]

I am currently a 5th year PhD student in the Computer Science Department, and a MS in the Statistics Department of Stanford University, advised by Fei-Fei Li. My research interests are in computer vision and applied machine learning. I am a Microsoft Research PhD Fellow and a Stanford Graduate Fellow.

I received a BE degree with honors from the Automation Department, and a ME degree with honors from the Department of Computer Science and Technology of Tsinghua University. I was a research intern in Microsoft Resarch Cambridge and Willow Garage Inc.




Sep 09-Present Jul 11-Sep 11 Jul 10-Sep 10 Sep 08-Aug 09 Sep 02-Jul 08
 
News
  • I have a CVPR 2013 oral paper accepted, co-authored with Vignesh Ramananthan (first author) and Li Fei-Fei. (March 2013)
  • An improvement of our discriminant RF method won the action classification taser of PASCAL VOC Challenge 2012 (October 2012).
  • I have an ECCV 2012 oral paper accepted, co-authored with Li Fei-Fei. (June 2012)
  • We released the code of our method that won PASCAL VOC 2011 Action Classification Challenge. Click here for details. The code is based on my CVPR 2011 paper with Aditya Khosla and Li Fei-Fei.
 
Research Interest

   Computer Vision: Human-object interaction analysis, action recognition, fine-grained object recognition, visual context modeling, object detection, scene recognition, face recognition, low-level feature representation.
   Machine Learning: Random fields, max-margin learning, boosting, graphical models, random forest, case-based reasoning.
   Computational Neuroscience: fMRI analysis.
 
Selected Honors & Awards
  • Microsoft Research PhD Fellowship, 2012-2013.
  • First Place in the action classification taser of PASCAL VOC Challenge, 2011,2012.
  • Outstanding Reviewer Award, ECCV 2012.
  • CVPR Best Paper Honorable Mentioin Award, 2010.
  • SAP Stanford Graduate Fellowship, 2010-2012.
  • Master Graduate with Highest Honor, Tsinghua University, 2008.
  • Bachelor Graduate with Highest Honor, Tsinghua University, 2006.
  • Scholarships: ESS (2007), Samsung (2005), Xianglu (2004), Schneider-Electric (2003).
 
Publication

Social Role Discovery in Human Events
 Vignesh Ramananthan, Bangpeng Yao, and Li Fei-Fei
 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, OR, USA. June 23-28, 2013.
 Oral presentation; Acceptance rate: 4.0%
 
Action Recognition with Exemplar Based 2.5D Graph Matching
 Bangpeng Yao and Li Fei-Fei
 European Conference on Computer Vision (ECCV). Firenze, Italy. October 7-13, 2012.
 Oral presentation; Acceptance rate: 3.6%   [pdf]  [BibTex]  [slides]  [Video Talk]
 
A Codebook-Free and Annotation-Free Approach for Fine-Grained Image Categorization
 Bangpeng Yao, Gary Bradski, and Li Fei-Fei
 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA. June 16-21, 2012.
 Acceptance rate: 24.1%   [pdf]  [poster]  [BibTex]
 
Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses
 Bangpeng Yao and Li Fei-Fei
 IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Volume 34, Issue 9, Pages 1691-1703, 2012.
 [pdf]
 
Human Action Recognition by Learning Bases of Action Attributes and Parts
 Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas J. Guibas, and Li Fei-Fei
 International Conference on Computer Vision (ICCV). Barcelona, Spain. November 6-13, 2011.
 Oral presentation; Acceptance rate: 3.6%   [pdf]  [full version]  [BibTex]  [slides]  [Video Talk]  [Stanford-40 Action Dataset]
 PASCAL Challenge Winning Prize (comp 10), 2011
 
Decision Tree Fields
 Sebastian Nowozin, Carsten Rother, Shai Bagon, Toby Sharp, Bangpeng Yao, and Pushmeet Kohli
 International Conference on Computer Vision (ICCV). Barcelona, Spain. November 6-13, 2011.
 Oral presentation; Acceptance rate: 3.6%   [pdf]  [Supplementary Doc]  [BibTex]
 
Classifying Actions and Measuring Action Similarity by Modeling the Mutual Context of Objects and Human Poses
 Bangpeng Yao, Aditya Khosla, and Li Fei-Fei
 International Conference on Machine Learning (ICML). Bellevue, WA, USA. June 28 - July 2, 2011.
 Oral presentation in the cross-conference track   [pdf]  [BibTex]  [slides]
 
Combining Randomization and Discrimination for Fine-Grained Image Categorization
 Bangpeng Yao*, Aditya Khosla*, and Li Fei-Fei  (* indicates equal contribution)
 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Colorado Springs, CO, USA. June 21-25, 2011.
 Acceptance rate: 26.4%   [pdf]  [BibTex]  [slides]  [source code]
 PASCAL Challenge Winning Prize (comp 9), 2011 & 2012
 
Grouplet: A Structured Image Representation for Recognizing Human and Object Interactions
 Bangpeng Yao and Li Fei-Fei
 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA, USA. June 13-18, 2010.
 Oral presentation; Acceptance rate: 4.5%   [pdf]  [full version]  [BibTex]  [slides]  [Video Talk]  [PPMI dataset]
 
Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities
 Bangpeng Yao and Li Fei-Fei
 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, CA, USA. June 13-18, 2010.
 Oral presentation; Acceptance rate: 4.5%   [pdf]  [full version]  [BibTex]  [slides]  [Video Talk]  [Data Annotation]
 CVPR Best Paper Honorable Mention Award, 2010
 
ANMM4CBR: A Case-Based Reasoning Method for Gene Expression Data Classification
 Bangpeng Yao and Shao Li
 Algorithms for Molecular Biology, 5:14, 2010.
 Highly accessed paper   [pdf]  [BibTex]
 
Hierarchical Mixture of Classification Experts Uncovers Interactions between Brain Regions
 Bangpeng Yao, Dirk B. Walther, Diane M. Beck, and Li Fei-Fei
 Annual Conference on Neural Information Processing Systems (NIPS). Vancouver, BC, Canada. December 7-10, 2009.
 Acceptance rate: 23.8%   [pdf]  [BibTex]  [poster]
 
Mining Discriminative Adjectives and Prepositions for Natural Scene Recognition
 Bangpeng Yao, Juan Carlos Niebles, and Li Fei-Fei
 International Workshop on Visual Scene Understanding (ViSU). Miami, FL, USA. June 25, 2009.
 Spotlight poster   [pdf]  [BibTex]  [poster]
 
Building a Compact Relevant Sample Coverage for Relevance Feedback in Content-Based Image Retrieval
 Bangpeng Yao, Haizhou Ai, and Shihong Lao
 European Conference on Computer Vision (ECCV). Marseille, France. October 12-18, 2008.
 Acceptance rate: 27.9%   [pdf]  [BibTex]
 
Logit-RankBoost with Pruning for Face Recognition
 Bangpeng Yao, Haizhou Ai, and Shihong Lao
 IEEE Conference on Automatic Face and Gesture Recognition (FG). Amsterdam, Netherlands. September 17-19, 2008.
 [pdf]  [BibTex]
 
Person-Specific Face Recognition in Unconstrained Environments: A Combination of Offline and Online Learning
 Bangpeng Yao, Haizhou Ai, and Shihong Lao
 IEEE Conference on Automatic Face and Gesture Recognition (FG). Amsterdam, Netherlands. September 17-19, 2008.
 [pdf]  [BibTex]
 
Matching Texture Units for Face Recognition
 Bangpeng Yao, Haizhou Ai, and Shihong Lao
 IEEE International Conference on Image Processing (ICIP). San Diego, TX, USA. October 12-15, 2008.
 [pdf]  [BibTex]
 
Domain-Partitioning RankBoost for Face Recognition
 Bangpeng Yao, Haizhou Ai, Yoshihisa Ijiri, and Shihong Lao
 IEEE International Conference on Image Processing (ICIP). San Antonio, TX, USA. September 16-19, 2007.
 Oral presentation   [pdf]  [BibTex]
 
Contact

    Email:
    Office:

 

bangpeng@cs.stanford.edu
Computer Science Building, Room 244
353 Serra Mall, Stanford University
Stanford, CA 94305-9025, USA

  Thank you for visiting my homepage!