Spatio-temporal information for human action recognition

Human activity recognition in videos is important for content-based videos indexing, intelligent monitoring, human-machine interaction, and virtual reality. This paper uses the low-level feature-based framework for human activity recognition which includes feature extraction and descriptor computing, early multi-feature fusion, video representation, and classification. This paper improves the first two steps. We propose a spatio-temporal bigraph-based multi-feature fusion algorithm to capture the useful visual information for recognition. Meanwhile, we introduce a compressed spatio-temporal video representation to bag of words representation. Our experiments on two popular datasets show efficient performance.

• Publication year

  2016

• Venue

  EURASIP Journal on Image and Video Processing

• Publication date

  2016-11-24

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1186/s13640-016-0145-2
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Human action recognition using fusion of features for unconstrained video sequences

  2016cited by this paper
• Modeling video evolution for action recognition

  2015cited by this paper
• Action recognition via structured codebook construction

  2014influential reference
• Compact Representation for Image Classification: To Choose or to Compress?

  2014cited by this paper
• Discriminant Bag of Words based representation for human action recognition

  2014cited by this paper
• Combining the Right Features for Complex Event Recognition

  2013cited by this paper
• A local descriptor based on Laplacian pyramid coding for action recognition

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

  2013cited by this paper
• Discovering joint audio–visual codewords for video event detection

  2013cited by this paper
• Multi-task Sparse Learning with Beta Process Prior for Action Recognition

  2013cited by this paper
• Multimodal feature fusion for robust event detection in web videos

  2012cited by this paper
• Learning latent temporal structure for complex event detection

  2012cited by this paper
• Action bank: A high-level representation of activity in video

  2012cited by this paper
• Aggregating Local Image Descriptors into Compact Codes

  2012cited by this paper
• Action recognition with multiscale spatio-temporal contexts

  2011influential reference
• Audio-visual grouplet: temporal audio-visual interactions for general video concept classification

  2011cited by this paper
• Recognizing human actions by attributes

  2011influential reference
• A review of optimization methodologies in support vector machines

  2011cited by this paper
• Learning a hierarchy of discriminative space-time neighborhood features for human action recognition

  2010influential reference
• Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification

  2010cited by this paper
• Object, Scene and Actions: Combining Multiple Features for Human Action Recognition

  2010cited by this paper
• Audio-visual atoms for generic video concept classification

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

  2009cited by this paper
• Recognising action as clouds of space-time interest points

  2009cited by this paper
• Actions in context

  2009cited by this paper
• Fast realistic multi-action recognition using mined dense spatio-temporal features

  2009cited by this paper
• Selection and context for action recognition

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

  2009cited by this paper
• Discriminative subvolume search for efficient action detection

  2009cited by this paper
• Action recognition by learning mid-level motion features

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

  2008cited by this paper
• Action Recognition in Broadcast Tennis Video

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

  2004cited by this paper
• A Divisive Information-Theoretic Feature Clustering Algorithm for Text Classification

  2003cited by this paper
• An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods

  2001cited by this paper
• An Introduction to Support Vector Machines and Other Kernel-based Learning Methods

  2000cited by this paper
• Recursive identification of gesture inputs using hidden Markov models

  1994cited by this paper

• Deep neuro-fuzzy system for violence detection

  2024cites this paper
• Review and Analysis of Patients’ Body Language From an Artificial Intelligence Perspective

  2023cites this paper
• goldenAGER: A Personalized Feature Fusion Activity Recognition Model for Elderly

  2023cites this paper
• KNN-Based Machine Learning Classifier Used on Deep Learned Spatial Motion Features for Human Action Recognition

  2023cites this paper
• SSHA: Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model

  2022cites this paper
• Real-Time Human Fault Detection in Assembly Tasks, Based on Human Action Prediction Using a Spatio-Temporal Learning Model

  2022cites this paper
• Spatio-Temporal Context, Correlation Filter and Measurement Estimation Collaboration Based Visual Object Tracking

  2021cites this paper
• Identification of Abnormal Movements in Infants: A Deep Neural Network for Body Part-Based Prediction of Cerebral Palsy

  2021cites this paper
• Machine Learning Model for Group Activity Recognition Based on Discriminative Interaction Contextual Relationship

  2021cites this paper
• School of Computer Science and Statistics Amobile exam proctoring system with deep-learning-based human action recognition

  2021cites this paper
• Robust Feature Extraction and Classification Based Automated Human Action Recognition System for Multiple Datasets

  2020cites this paper
• HUMAN ACTIVITY DETECTION AND ACTION RECOGNITION IN VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS

  2020cites this paper
• R-STDP Based Spiking Neural Network for Human Action Recognition

  2020cites this paper
• A computationally efficient method for Human Activity Recognition based on spatio temporal cuboid and Super Normal Vector

  2020cites this paper
• Abnormal Infant Movements Classification With Deep Learning on Pose-Based Features

  2020cites this paper
• Citation: Mccay, Kevin, Ho, Edmond, Marcroft, Claire and Embleton, Nicholas D. (2019) Establishing Pose Based Features Using Histograms for the Detection of Abnormal Infant

  2019cites this paper
• Establishing Pose Based Features Using Histograms for the Detection of Abnormal Infant Movements

  2019cites this paper
• Vector space based augmented structural kinematic feature descriptor for human activity recognition in videos

  2018cites this paper
• Versatile loitering detection based on non-verbal cues using dense trajectory descriptors

  2018cites this paper