Online Vision-Based Eye Detection: LBP/SVM vs LBP/LSTM-RNN

Benrachou, Djamel Eddine; Santos, Filipe Neves dos; Boulebtateche, Brahim; Bensaoula, Salah

doi:10.1007/978-3-319-10380-8_63

Cited by 8 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, in [14], the authors have shown the effects of understanding human gaze communication by spatio-temporal graph reasoning, which allows us to see the real relationship between the behavior of people and the stimuli, showing that their interpretation and humans have the unique ability to infer others' intentions from eye gazes [13]. This approach with LSTM models is also followed by other authors [6,8,23].…”

Section: Overview Of the Related Workmentioning

confidence: 90%

“…At an instant t, there is an input value for the winner, I t,winner , and an input value for every k loser, I t,k . The process is modeled as an optimization problem, where the aim is to obtain the optimal weights that maximize the sum of the distances between the winners and the losers at each time instant t, as shown in (6). This procedure ensures that the weights are optimal to make the selected persons winners and separate them from the losers.…”

Section: Weight Stimuli Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Optimization and improvement of a robotics gaze control system using LSTM networks

Domingo

Gómez-García-Bermejo

Zalama

2021

Multimed Tools Appl

View full text Add to dashboard Cite

Gaze control represents an important issue in the interaction between a robot and humans. Specifically, deciding who to pay attention to in a multi-party conversation is one way to improve the naturalness of a robot in human-robot interaction. This control can be carried out by means of two different models that receive the stimuli produced by the participants in an interaction, either an on-center off-surround competitive network or a recurrent neural network. A system based on a competitive neural network is able to decide who to look at with a smooth transition in the focus of attention when significant changes in stimuli occur. An important aspect in this process is the configuration of the different parameters of such neural network. The weights of the different stimuli have to be computed to achieve human-like behavior. This article explains how these weights can be obtained by solving an optimization problem. In addition, a new model using a recurrent neural network with LSTM layers is presented. This model uses the same set of stimuli but does not require its weighting. This new model is easier to train, avoiding manual configurations, and offers promising results in robot gaze control. The experiments carried out and some results are also presented.

show abstract