Recognizing gaze aversion gestures in embodied conversational discourse

Morency, Louis–Philippe; Christoudias, C. Mario; Darrell, Trevor

doi:10.1145/1180995.1181051

Cited by 49 publications

(37 citation statements)

References 37 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These "thinking" gaze gestures are saccades in the direction of uninformative regions of space that are often subtle and difficult even for humans to identify [11]. Algorithms that can detect turn-management gaze gestures and "thinking" gaze aversion gestures are needed for the design of naturalistic ECAs.…”

Section: Previous Work On Gaze Aversionmentioning

confidence: 99%

“…However, the classification problem of conversational gaze aversion detection has received less attention. In [11], Morency et al proposed an SVM-based approach that discriminates "thinking" gaze aversion gestures from eye contact and deictic gestures (saccades that reference a specific object or person of interest) using temporal windows of eye gaze directions. In [14] the SVM-based approach is improved upon with the use of Latent-Dynamic Conditional Random Fields (LDCRFs).…”

Section: Previous Work On Gaze Aversionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting conversational gaze aversion using unsupervised learning

Roddy

Harte

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-The aversion of gaze during dyadic conversations is a social signal that contains information relevant to the detection of interest, turn-taking cues, and conversational engagement. The understanding and modeling of such behavior has implications for the design of embodied conversational agents, as well as computational approaches to conversational analysis. Recent approaches to extracting gaze directions from monocular camera footage have achieved accurate results. We investigate ways of processing the extracted gaze signals from videos to perform gaze aversion detection. We present novel approaches that are based on unsupervised classification using spectral clustering as well as optimization methods. Three approaches that vary in their input parameters and their complexity are proposed and evaluated.

show abstract

Section: Previous Work On Gaze Aversionmentioning

confidence: 99%

Section: Previous Work On Gaze Aversionmentioning

confidence: 99%

Detecting conversational gaze aversion using unsupervised learning

Roddy

Harte

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

“…Deictic gestures are eye gestures with a specific reference to an uninvolved person or an object. Non deictic gestures or gaze averting are eye movements to empty or uninformative regions of space [25]. Hybrid methods combines the advantages of different eye models like colours and shape, shape and intensity etc.…”

Section: Eye Gaze Techniquesmentioning

confidence: 99%

“…The 3D based model eye tracking systems require one time system and geometric calibration with natural head movements [4,25,35]. Although the 3D-based method is more accurate than the 2D-based one, the former requires much more processing time and requires complicated calibrations between the camera and monitor, which makes it difficult to be used for large-sized display interfaces [34].…”

Section: Eye Gaze Techniquesmentioning

confidence: 99%

Eye Gaze Techniques for Human Computer Interaction: A Research Survey

Sharma¹,

Abrol²

2013

IJCA

View full text Add to dashboard Cite

Human Computer Interaction (HCI) is an emerging technology. Eye gaze technique is one of the very significant techniques of HCI and can be used as hands free pointing tool enabling hands-free operation of the display for the user. The important advantage in using eye gaze systems is that the user can communicate from a distance, and there is no requirement of physical contact with the computer. Investigation of eye gaze helps to understand various aspects of the user like attention, intention, desire and area of interest etc. The eye gaze detection techniques can be classified on the basis of direct eye detection, appearance, template, shape, feature, motion, hybrid, regression, 3D methods etc. There are significant factors like shape and size of the object, distance from the subject, texture, light conditions, colour, orientation, head movement, calibration which may influence and affect the efficiency and effectiveness of the eye gaze detection. The use of the gaze as a human computer interface in different fields is an example of high end applications of these techniques. Eye detection is being used in many real time and interactive high end applications. These include the tracking and analyzing of driver"s behaviour with the head pose detection. It is being used for assessing consumer"s shopping behaviour, pointing and selection, activating commands and combinations with other pointing devices, in surgical and medical applications. Moreover eye gaze techniques are also useful for designing and development of various devices especially for differently abled users.In this paper an extensive research survey has been carried out to understand and analyze the study of various eye gaze techniques, algorithms and models. On the basis of survey of various techniques of eye gaze, a general overview of different phases of eye gaze processing has been presented. Certain technical factors have been identified that are significant and relevant for the working of the models. In the literature survey a number of parameters that are significant for estimation, detection, better efficiency and accuracy of eye gaze techniques have been studied and analysed. A comparison and analytical discussion of different eye gaze techniques and models have been presented. The analysis and classification of the models shall be helpful for further improvement and optimization in the performance and accuracy of eye gaze techniques. General TermHuman computer interaction. KeywordsEye gaze techniques and models, feature based classification and comparison, phases, gaze detection and estimation.

show abstract

“…For the robots discussed above, this basically comes down to machine vision and spoken dialogue understanding. Machine vision research has progressed significantly in recent years, notably including the development of reliable algorithms for face tracking (Viola and Jones 2001), human limb tracking (Demirdjian 2004), face recognition (Moghaddam, Jebara, and Pentland 2000) and gaze recognition (Morency, Christoudias, and Darrell 2006). There have also been limited improvements in object recognition (Torralba, Murphy, and Freeman 2004;Liebe et al 2007), which is important for applications of human-robot interaction, such as collaborative assembly.…”

Section: Geminoid (With Creator At Left)mentioning

confidence: 99%

Robots and Avatars as Hosts, Advisors, Companions, and Jesters

Rich

Sidner

2009

AI Magazine

View full text Add to dashboard Cite

In the 1970s, some AI leaders predicted that we would soon see all manner of artificially intelligent entities in our daily lives. Unfortunately, in the interim, this has been true mostly in the realm of science fiction. Recently, however, pioneering researchers have been bringing together advances in many subfields of AI, such as robotics, computer vision, natural language and speech processing, and cognitive modeling, to create the first generation of robots and avatars that illustrate the true potential of combining these technologies. The purpose of this article is to highlight a few of these projects and to draw some conclusions from them for future research.We begin with a short discussion of scope and terminology. Our focus here is on how robots and avatars interact with humans, rather than with the environment. Obviously, this cannot be a sharp distinction, since humans form part of the environment for such entities. However, we are interested primarily in how new interaction capabilities enable robots and avatars to enter into new kinds of relationships with humans, such as hosts, advisors, companions, and jesters.We will not try to define robot here, but we do want to point out that our focus is on humanoid robots (although we stretch the category a bit to include a few animallike robots that illustrate the types of interaction we are interested in). Industrial automation robotics, while economically very important, and a continual source of advances in sensor and effector technology for humanoid robots, will continue to be more of a behind-the-scenes contributor to our everyday lives.The meaning of the term avatar is currently in flux. Its original and narrowest use is to refer to the graphical representation of a person (user) in a virtual reality system. Recently, however, the required con-

show abstract

Recognizing gaze aversion gestures in embodied conversational discourse

Cited by 49 publications

References 37 publications

Detecting conversational gaze aversion using unsupervised learning

Detecting conversational gaze aversion using unsupervised learning

Eye Gaze Techniques for Human Computer Interaction: A Research Survey

Robots and Avatars as Hosts, Advisors, Companions, and Jesters

Contact Info

Product

Resources

About