Log In Sign Up

Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification

by   Amir Ahooye Atashin, et al.

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.


page 1

page 3

page 4


What's the point? Frame-wise Pointing Gesture Recognition with Latent-Dynamic Conditional Random Fields

We use Latent-Dynamic Conditional Random Fields to perform skeleton-base...

The Recurrent Temporal Discriminative Restricted Boltzmann Machines

The recurrent temporal restricted Boltzmann machine (RTRBM) has been suc...

CTCModel: a Keras Model for Connectionist Temporal Classification

We report an extension of a Keras Model, called CTCModel, to perform the...

Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video

Recent studies have demonstrated the power of recurrent neural networks ...

Sequence Modeling via Segmentations

Segmental structure is a common pattern in many types of sequences such ...

Complexity-Aware Assignment of Latent Values in Discriminative Models for Accurate Gesture Recognition

Many of the state-of-the-art algorithms for gesture recognition are base...

Recognizing Surgical Activities with Recurrent Neural Networks

We apply recurrent neural networks to the task of recognizing surgical a...