| Probabilistic Models: temporal topic models and more | ||
List of Related PublicationsThis page lists the main papers related to this website and that must be cited in reference to these methods and their implementations. Probabilistic Latent Sequential Motifs (PLSM)About the PLSM temporal topic model. A Sequential Topic Model for Mining Recurrent Activities from Long Term Video Logs. [bibtex] (click to show)
@article{VaradarajanIJCV2O13,
author = {Jagannadan Varadarajan and R{\'e}mi Emonet and Jean-Marc Odobez},
title = {A Sequential Topic Model for Mining Recurrent Activities from Long Term Video Logs},
journal = {International Journal of Computer Vision},
volume = {103},
number = {1},
year = {2013},
pages = {100-126},
ee = {http://dx.doi.org/10.1007/s11263-012-0596-6}
}
Probabilistic Latent Sequential Motifs: Discovering temporal activity patterns in video scenes. [bibtex] (click to show)
@INPROCEEDINGS{VaradarajanBMVC2010,
author = {Varadarajan, Jagannadan and Emonet, Remi and Odobez, Jean-Marc},
projects = {SNSF-MULTI},
month = {9},
title = {Probabilistic Latent Sequential Motifs: Discovering temporal activity patterns in video scenes},
booktitle = {BMVC},
year = {2010},
publisher = {BMVA Press},
location = {Aberystwyth},
organization = {Aberystwyth University},
crossref = {Varadarajan_Idiap-RR-33-2010}
}
Applying PLSM for anomaly detection in with multiple cameras. Multi-camera Open Space Human Activity Discovery for Anomaly Detection. [bibtex] (click to show)
@INPROCEEDINGS{EmonetAVSS2011,
author = {Rémi Emonet and Jagannadan Varadarajan and Jean-Marc Odobez},
title = {{Multi-camera Open Space Human Activity Discovery for Anomaly Detection}},
booktitle = {2011 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS)},
year = {2011},
pages = {6},
month = {Aug.}
}
About the sparsity constraint in topic models (including PLSM). A Sparsity Constraint for Topic Models — Application to Temporal Activity Mining. [bibtex] (click to show)
@INPROCEEDINGS{VaradarajanNIPS2010WS,
author = {Varadarajan, Jagannadan and Emonet, Remi and Odobez, Jean-Marc},
projects = {Idiap, SNSF-MULTI},
month = {12},
title = {A Sparsity Constraint for Topic Models - Application to Temporal Activity Mining},
booktitle = {NIPS-2010 Workshop on Practical Applications of Sparse Modeling: Open Issues and New Directions},
year = {2010},
crossref = {Varadarajan_Idiap-RR-36-2010}
}
Motivating temporal topic models for mixed-activity temporal data logs. Extracting Motifs from Time Series Generated by Concurrent Activities. [bibtex] (click to show)
@INPROCEEDINGS{VaradarajanNIPS2010TS,
author = {Varadarajan, Jagannadan and Emonet, Remi and Odobez, Jean-Marc},
projects = {Idiap, SNSF-MULTI},
month = {12},
title = {Extracting Motifs from Time Series Generated by Concurrent Activities},
booktitle = {NIPS-2010 Workshop on Learning and Planning from Batch Time Series Data},
year = {2010},
crossref = {Varadarajan_Idiap-RR-36-2010}
}
Non Parametric Models (HDLSM, TAMM, VLTAMM, etc.)About HDLSM temporal topic model, the Bayesian non-parametric interpretation of PLSM. Temporal Analysis of Motif Mixtures using Dirichlet Processes. [bibtex] (click to show)
@ARTICLE{EmonetPAMI2013,
author = {Emonet, Remi and Varadarajan, Jagannadan and Odobez, Jean-Marc},
title = {Temporal Analysis of Motif Mixtures using Dirichlet Processes},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2013}
}
Extracting and Locating Temporal Motifs in Video Scenes Using a Hierarchical Non Parametric Bayesian Model. [bibtex] (click to show)
@INPROCEEDINGS{EmonetCVPR2011,
author = {Emonet, Remi and Varadarajan, Jagannadan and Odobez, Jean-Marc},
projects = {Idiap, SNSF-MULTI, VANAHEIM},
month = jun,
title = {Extracting and Locating Temporal Motifs in Video Scenes Using a Hierarchical Non Parametric Bayesian Model},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2011}
}
Other following worksAbout adding higher level modelling to capture scene-level rules (MER model). Bridging the Past, Present and Future: Modeling Scene Activities From Event Relationships and Global Rules. [bibtex] (click to show)
@INPROCEEDINGS{Varadarajan_CVPR_2012,
author = {Varadarajan, Jagannadan and Emonet, Remi and Odobez, Jean-Marc},
month = jun,
title = {Bridging the Past, Present and Future: Modeling Scene Activities From Event Relationships and Global Rules},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition, 2012, Providence, Rhode Island, USA},
year = {2012}
}
About the use of temporal topic models for action recognition. Time-Sensitive Topic Models for Action Recognition in Videos. [bibtex] (click to show)
@INPROCEEDINGS{TavenardICIP2013,
author={Romain Tavenard and Rémi Emonet and Jean-Marc Odobez},
title={Time-Sensitive Topic Models for Action Recognition in Videos},
booktitle={IEEE International Conference on Image Processing},
year={2013}
}
|
||