Learning Time Series Segmentation Models from Temporally Imprecise Labels

Roy Adams, Benjamin M. Marlin
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:134-143, 2018.

Abstract

This paper considers the problem of learning time series segmentation models when the labeled data are subject to temporal uncertainty or noise. Our approach augments the semi- Markov conditional random field (semi-CRF) model with a probabilistic model of the label observation process. This augmentation allows us to estimate the parameters of the semi-CRF from timestamps corresponding roughly to the occurrence of transitions between segments. We show how exact marginal inference can be performed in the augmented model in polynomial time, enabling learning based on marginal likelihood maximization. Our experiments on two activity detection problems show that the proposed approach can learn models from temporally imprecise labels, and can successfully refine imprecise segmentations through posterior inference. Finally, we show how inference complexity can be reduced by a factor of 40 using static and model-based pruning of the inference dynamic program.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-adams18a, title = {Learning Time Series Segmentation Models from Temporally Imprecise Labels}, author = {Adams, Roy and Marlin, Benjamin M.}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {134--143}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/adams18a/adams18a.pdf}, url = {https://proceedings.mlr.press/r16/adams18a.html}, abstract = {This paper considers the problem of learning time series segmentation models when the labeled data are subject to temporal uncertainty or noise. Our approach augments the semi- Markov conditional random field (semi-CRF) model with a probabilistic model of the label observation process. This augmentation allows us to estimate the parameters of the semi-CRF from timestamps corresponding roughly to the occurrence of transitions between segments. We show how exact marginal inference can be performed in the augmented model in polynomial time, enabling learning based on marginal likelihood maximization. Our experiments on two activity detection problems show that the proposed approach can learn models from temporally imprecise labels, and can successfully refine imprecise segmentations through posterior inference. Finally, we show how inference complexity can be reduced by a factor of 40 using static and model-based pruning of the inference dynamic program.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Learning Time Series Segmentation Models from Temporally Imprecise Labels %A Roy Adams %A Benjamin M. Marlin %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-adams18a %I PMLR %P 134--143 %U https://proceedings.mlr.press/r16/adams18a.html %V R16 %X This paper considers the problem of learning time series segmentation models when the labeled data are subject to temporal uncertainty or noise. Our approach augments the semi- Markov conditional random field (semi-CRF) model with a probabilistic model of the label observation process. This augmentation allows us to estimate the parameters of the semi-CRF from timestamps corresponding roughly to the occurrence of transitions between segments. We show how exact marginal inference can be performed in the augmented model in polynomial time, enabling learning based on marginal likelihood maximization. Our experiments on two activity detection problems show that the proposed approach can learn models from temporally imprecise labels, and can successfully refine imprecise segmentations through posterior inference. Finally, we show how inference complexity can be reduced by a factor of 40 using static and model-based pruning of the inference dynamic program. %Z Reissued by PMLR on 04 October 2026.
APA
Adams, R. & Marlin, B.M.. (2018). Learning Time Series Segmentation Models from Temporally Imprecise Labels. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:134-143 Available from https://proceedings.mlr.press/r16/adams18a.html. Reissued by PMLR on 04 October 2026.

Related Material