Human action segmentation and recognition using discriminative semi-Markov models

DOI10.1007/S11263-010-0384-0zbMATH Open1235.68287OpenAlexW2014914041MaRDI QIDQ408910FDOQ408910

Authors Qinfeng Shi, Alex J. Smola, Li Cheng, Li Wang 

Publication date 12 April 2012

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11263-010-0384-0

zbMATH Keywords

semi-Markov modelaction segmentation and recognitionlarge-margin method

Mathematics Subject Classification ID

Machine vision and scene understanding (68T45)

Recommendations

• Boosted multi-class semi-supervised learning for human action recognition
• Incremental discriminant-analysis of canonical correlations for action recognition
• Space-time tree ensemble for action recognition and localization
• Human action recognition based on fusion features extraction of adaptive background subtraction and optical flow model
• Learning discriminative localization from weakly labeled data

Cites work

• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• Computable shell decomposition bounds
• Human action segmentation and recognition using discriminative semi-Markov models
• Large margin methods for structured and interdependent output variables
• PAC-Bayesian stochastic model selection
• Simplified PAC-Bayesian margin bounds.
• Some results on Tchebycheffian spline functions and stochastic processes
• The Visual Analysis of Human Movement: A Survey

Cited in

(13)

• Boosted multi-class semi-supervised learning for human action recognition
• Discriminatively learned hierarchical rank pooling networks
• Space-time tree ensemble for action recognition and localization
• Harnessing lab knowledge for real-world action recognition
• Discriminative hierarchical part-based models for human parsing and action recognition
• Human action segmentation and recognition using discriminative semi-Markov models
• Learning discriminative localization from weakly labeled data
• Real-time online action detection and segmentation using improved efficient linear search
• Online recognition of human actions based on temporal deep belief neural network
• Action categorization with modified hidden conditional random field
• Complex activity recognition via attribute dynamics
• Hand gesture recognition based on dynamic Bayesian network framework
• Latent structured models for video understanding

Describes a project that uses

Uses Software

• SIFT

This page was built for publication: Human action segmentation and recognition using discriminative semi-Markov models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q408910)