6th International Conference on Computer and Knowledge Engineering , 2016-10-13

Title : ( Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification )

Authors: Amir Ahooye Atashin , Kamaledin Ghiasi Shirazi , Ahad Harati ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Many machine learning problems such as speech recognition, gesture recognition, and handwriting recognition are concerned with simultaneous segmentation and labeling of sequence data. Latent-dynamic conditional random field (LDCRF) is a well-known discriminative method that has been successfully used for this task. However, LDCRF can only be trained with pre-segmented data sequences in which the label of each frame is available apriori. In the realm of neural networks, the invention of connectionist temporal classification (CTC) made it possible to train recurrent neural networks on unsegmented sequences with great success. In this paper, we use CTC to train an LDCRF model on unsegmented sequences. Experimental results on two gesture recognition tasks show that the proposed method outperforms LDCRFs, hidden Markov models, and conditional random fields.

Keywords

, Latent, dynamic conditional random fields; connectionist temporal classification; unsegmented
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@inproceedings{paperid:1057677,
author = {Ahooye Atashin, Amir and Ghiasi Shirazi, Kamaledin and Harati, Ahad},
title = {Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification},
booktitle = {6th International Conference on Computer and Knowledge Engineering},
year = {2016},
location = {مشهد, IRAN},
keywords = {Latent-dynamic conditional random fields; connectionist temporal classification; unsegmented sequences;},
}

[Download]

%0 Conference Proceedings
%T Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification
%A Ahooye Atashin, Amir
%A Ghiasi Shirazi, Kamaledin
%A Harati, Ahad
%J 6th International Conference on Computer and Knowledge Engineering
%D 2016

[Download]