A sequential topic model for mining recurrent activities from long term video logs

DOI10.1007/s11263-012-0596-6zbMath1270.68357OpenAlexW1979350646MaRDI QIDQ362077

Jagannadan Varadarajan, Jean-Marc Odobez, Rémi Emonet

Publication date: 20 August 2013

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

Full work available at URL: https://infoscience.epfl.ch/record/192689/files/Varadarajan_IJCV_2012.pdf

zbMATH Keywords

topic modelsvideo surveillanceactivity analysislatent sequential patternsPLSAunsupervised

Mathematics Subject Classification ID

Machine vision and scene understanding (68T45)

Related Items (1)

Additive regularization of topic models

Cites Work

• Unnamed Item
• A correlated topic model of science
• Estimating the dimension of a model
• Discovery of time-series motif from multi-dimensional data based on MDL principle
• Video behaviour mining using a dynamic topic model
• Hierarchical Dirichlet Processes
• 10.1162/jmlr.2003.3.4-5.993
• A new look at entropy for solving linear inverse problems
• Unsupervised learning by probabilistic latent semantic analysis
• Non-parametric motion activity analysis for statistical retrieval with partial query
• Dimensionality reduction for fast similarity search in large time series databases

This page was built for publication: A sequential topic model for mining recurrent activities from long term video logs