Spatio-temporal Aware Non-negative Component Representation for Action Recognition

This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR). The proposed STANNCR is based on action component and incorporates the spatial-temporal information. We first introduce a spatial-temporal distribution vector (STDV) to model the distributions of local feature locations in a compact and discriminative manner. Then we employ non-negative matrix factorization (NMF) to learn the action components and encode the video samples. The action component considers the correlations of visual words, which effectively bridge the sematic gap in action recognition. To incorporate the spatial-temporal cues for final representation, the STDV is used as the part of graph regularization for NMF. The fusion of spatial-temporal information makes the STANNCR more discriminative, and our fusion manner is more compact than traditional method of concatenating vectors. The proposed approach is extensively evaluated on three public datasets. The experimental results demonstrate the effectiveness of STANNCR for action recognition.

• Publication year

  2016

• Venue

  arXiv.org

• Publication date

  2016-08-27

• Fields of study

  Computer Science

• Identifiers
  arXiv 1608.07664
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Parameter-less Auto-weighted multiple graph regularized Nonnegative Matrix Factorization for data representation

  2017cited by this paper
• STAP: Spatial-Temporal Attention-Aware Pooling for Action Recognition

  2015cited by this paper
• Local non-negative component representation for human action recognition

  2014cited by this paper
• Action Recognition Using Nonnegative Action Component Representation and Sparse Basis Selection

  2014influential reference
• Action Recognition Using Super Sparse Coding Vector with Spatio-temporal Awareness

  2014influential reference
• Action and Event Recognition with Fisher Vectors on a Compact Feature Set

  2013cited by this paper
• Sampling Strategies for Real-Time Action Recognition

  2013influential reference
• Space-Time Robust Representation for Action Recognition

  2013cited by this paper
• Dense Trajectories and Motion Boundary Descriptors for Action Recognition

  2013cited by this paper
• Recognizing Activities via Bag of Words for Attribute Dynamics

  2013cited by this paper
• Motionlets: Mid-level 3D Parts for Human Motion Recognition

  2013cited by this paper
• Classifying web videos using a global video descriptor

  2013cited by this paper
• Graph regularized discriminative non-negative matrix factorization for face recognition

  2013cited by this paper
• Action bank: A high-level representation of activity in video

  2012cited by this paper
• Trajectory-Based Modeling of Human Actions with Motion Reference Points

  2012influential reference
• Discovering discriminative action parts from mid-level video representations

  2012cited by this paper
• Scene Aligned Pooling for Complex Video Recognition

  2012cited by this paper
• Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis

  2011cited by this paper
• Learning spatiotemporal graphs of human activities

  2011cited by this paper
• HMDB: A large video database for human motion recognition

  2011cited by this paper
• A probabilistic representation for efficient large scale visual recognition tasks

  2011influential reference
• Recognizing human actions by attributes

  2011cited by this paper
• Action recognition with multiscale spatio-temporal contexts

  2011cited by this paper
• Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin

  2011cited by this paper
• Relative attributes

  2011cited by this paper
• In defense of soft-assignment coding

  2011cited by this paper
• Modeling spatial layout with fisher vectors for image categorization

  2011influential reference
• The devil is in the details: an evaluation of recent feature encoding methods

  2011cited by this paper
• A survey on vision-based human action recognition

  2010cited by this paper
• Discriminative human action recognition in the learned hierarchical manifold space

  2010cited by this paper
• Locality-constrained Linear Coding for image classification

  2010cited by this paper
• Recognizing realistic actions from videos “in the wild”

  2009cited by this paper
• Linear spatial pyramid matching using sparse coding for image classification

  2009cited by this paper
• Hierarchical spatio-temporal context modeling for action recognition

  2009cited by this paper
• A Spatio-Temporal Descriptor Based on 3D-Gradients

  2008cited by this paper
• Machine Recognition of Human Activities: A Survey

  2008cited by this paper
• Learning realistic human actions from movies

  2008influential reference
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  2006cited by this paper
• Recognizing human actions: a local SVM approach

  2004cited by this paper
• Learning the parts of objects by non-negative matrix factorization

  1999cited by this paper
• Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Convolutional Neural Networks for Human Action Recognition

  year unknowninfluential reference

• No citing papers are available for this paper.