Latent structured models for video understanding

MaRDI QIDQ2875317zbMATH OpenFDO

Authors Borislav Antić

Publication date 14 August 2014

Full work available at URL http://archiv.ub.uni-heidelberg.de/volltextserver/17157/1/phd-thesis.pdf

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to computer science (68-02) Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45) Computing methodologies for image processing (68U10)

Recommendations

• Temporal action detection with structured segment networks
• Human action segmentation and recognition using discriminative semi-Markov models
• Video behaviour mining using a dynamic topic model
• A sequential topic model for mining recurrent activities from long term video logs
• Generating open world descriptions of video using common sense knowledge in a pattern theory framework

Cited in

(3)

• Computer Vision - ECCV 2004
• Stratification approach to modeling video
• Deep low-rank matrix factorization with latent correlation estimation for micro-video multi-label classification

This page was built for publication: Latent structured models for video understanding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2875317)