Leo Zhu

   Postdoctoral Associate in Bill Freeman's group

   32-D462, Stata Center

   leo zhu AT csail dot mit dot edu



My research interests are statistical machine learning, computational vision and graphics, with particular emphasis on learning models for visual patterns such as textures, objects and image scenes.

[Projects] [Publications] [Download] [Dataset]

Object Detection: PASCAL

Long Zhu, Yuanhao Chen, Alan Yuille, William Freeman. Latent Hierarchical Structural Learning for Object Detection. CVPR 2010. [pdf]

Yuanhao Chen, Long Zhu, Alan Yuille. Active Mask Hierarchies for Object Detection. ECCV 2010. [pdf]

Presentation at PASCAL Visual Object Classes Challenge Workshop 2010.


Image Segmentation and Scene Labeling : MSRC and PASCAL

Long Zhu, Yuanhao Chen, Yuan Lin, Chenxi Lin, Alan Yuille. Recursive Segmentation and Recognition Templates for Image Parsing. PAMI. Under review Oct. 2009. [pdf]


Pose Estimation and Alignment: Berkeley Human ,Weizmann Horse and Face

Long Zhu, Yuanhao Chen, Chenxi Lin, Alan Yuille. Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation. IJCV 2010. [pdf] [dataset]

Long Zhu, Yuanhao Chen, Alan Yuille. Learning a Hierarchical Deformable Template for Rapid Deformable Object Parsing.  TPAMI 2010. [pdf

Data sets: [horse ground truth] [horse images] [training/validation/testing split] [testing results] [cow ground truth] [cow images]


Face Detection: CMU Face

Rong Xiao, Long Zhu, HongJiang Zhang. Boosting Chain Learning for Object Detection. ICCV 2003  [dataset]