Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin

Authors:
Yang Wang;Greg Mori
Affiliations:
University of Illinois at Urbana-Champaign, Urbana;Simon Fraser University, Burnaby
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2011

Citing 0
Cited 10

Recognizing interaction between human performers using 'key pose doublet'

MM '11 Proceedings of the 19th ACM international conference on Multimedia
Similarity constrained latent support vector machine: an application to weakly supervised action classification

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Recognizing expressions from face and body gesture by temporal normalized motion and appearance features

Image and Vision Computing
Multi-view action recognition based on action volumes, fuzzy distances and cluster discriminant analysis

Signal Processing
Data decomposition and spatial mixture modeling for part based model

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Learning latent spatio-temporal compositional model for human action recognition

Proceedings of the 21st ACM international conference on Multimedia
Object class detection: A survey

ACM Computing Surveys (CSUR)
Dynamic action recognition based on dynemes and Extreme Learning Machine

Pattern Recognition Letters
Matching mixtures of curves for human action recognition

Computer Vision and Image Understanding
Activity representation with motion hierarchies

International Journal of Computer Vision

Quantified Score

Hi-index	0.14

Visualization

Abstract

We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditional random field (HCRF) for object recognition. Similarly to HCRF for object recognition, we model a human action by a flexible constellation of parts conditioned on image observations. Differently from object recognition, our model combines both large-scale global features and local patch features to distinguish various actions. Our experimental results show that our model is comparable to other state-of-the-art approaches in action recognition. In particular, our experimental results demonstrate that combining large-scale global features and local patch features performs significantly better than directly applying HCRF on local patches alone. We also propose an alternative for learning the parameters of an HCRF model in a max-margin framework. We call this method the max-margin hidden conditional random field (MMHCRF). We demonstrate that MMHCRF outperforms HCRF in human action recognition. In addition, MMHCRF can handle a much broader range of complex hidden structures arising in various problems in computer vision.