Human Action Recognition by Learning Bases of Action Attributes and Parts

1
Human Action Recognition by Learning Bases of
Action Attributes and Parts

• Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy
  Lai Lin, Leonidas Guibas, and Li Fei-Fei
• Stanford University

2
Outline

• Introduction
• Action Bases
• Learning the Dual-Sparse Action Bases and
  Reconstruction Coefficients
• Experiments

3
Introduction

• Human action recognition in still images
• A general image classification problem
• Human-object interaction
• Parts Attributes
• Contributions
• Represent each image by using a sparse set of
  action bases that are meaningful to the content
  of the image
• Effectively learn these bases given
  far-from-perfect detections of action attributes
  and parts without meticulous human labeling

4
Action Bases

• Attributes and parts
• Attributes verb, learned by discriminative
  classifiers
• Parts object parts and poselets, learned by
  pre-trained object detectors and poselet
  detectors
• A vector of the normalized confidence scores
  obtained from these classifiers and detectors is
  used to represent this image.

5
Action Bases

• High-order interactions of image attributes and
  parts
• is used to represent
  each image and SVMs are trained for action
  classification

6
Dual-sparsity Learning
7
(No Transcript)
8
Experiments

• PASCAL actions
• Stanford 40 actions

9

• PASCAL

10

• Stanford 40 actions