Predicting Levels of Rapport in Dyadic Interactions through Automatic Detection of Posture and Posture Congruence

Hagad, Juan Lorenzo; Legaspi, Roberto; Numao, Masayuki; Suarez, Merlin Teodosia

doi:10.1109/passat/socialcom.2011.143

Cited by 15 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leite et al [5] studied the individual engagement estimation in group settings in the context of human-robot interaction. Hagad et al [6] automatically predicted rapport in dyadic interactions based on posture and congruence. Gallagher et al [1] introduced a framework to perform individual analysis, i.e., age and gender recognition by using contextual features that captured the structure of people in the image instead of using features from each individual.…”

Section: Related Workmentioning

confidence: 99%

“…More recently, other research fields, including emotion recognition, have also started to shift their focus from individual to group settings [3], [4]. Research works focusing on the analysis of social dimensions, such as engagement and rapport in group settings have also been introduced [5], [6]. Most of the aforementioned works analyze what is happening within the group.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generic to Specific Recognition Models for Membership Analysis in Group Videos

Mou

Tzelepis

Mezaris

et al. 2017

2017 12th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2017)

View full text Add to dashboard Cite

Automatic understanding and analysis of groups has attracted increasing attention in the vision and multimedia communities in recent years. However, little attention has been paid to the automatic analysis of group membership-i.e., recognizing which group the individual in question is part of. This paper presents a novel two-phase Support Vector Machine (SVM) based specific recognition model that is learned using an optimized generic recognition model. We conduct a set of experiments using a database collected to study group analysis from multimodal cues while each group (i.e., four participants together) were watching a number of long movie segments. Our experimental results show that the proposed specific recognition model (52%) outperforms the generic recognition model trained across all different videos (35%) and the independent recognition model trained directly on each specific video (33%) using linear SVM.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Generic to Specific Recognition Models for Membership Analysis in Group Videos

Mou

Tzelepis

Mezaris

et al. 2017

2017 12th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2017)

View full text Add to dashboard Cite

Automatic understanding and analysis of groups has attracted increasing attention in the vision and multimedia communities in recent years. However, little attention has been paid to the automatic analysis of group membership-i.e., recognizing which group the individual in question is part of. This paper presents a novel two-phase Support Vector Machine (SVM) based specific recognition model that is learned using an optimized generic recognition model. We conduct a set of experiments using a database collected to study group analysis from multimodal cues while each group (i.e., four participants together) were watching a number of long movie segments. Our experimental results show that the proposed specific recognition model (52%) outperforms the generic recognition model trained across all different videos (35%) and the independent recognition model trained directly on each specific video (33%) using linear SVM.

show abstract

“…In recent years, researchers have shown that it is possible to automatically detect complex social phenomena, often using predominantly or only nonverbal behavior; from dominance [15,20,21,26,39,43], functional roles [12,28,54], deception [7,40], cohesion [24], attraction [29,30,41,49], interest [16,36,48,52], influence [38,44], rapport [19,46], to friendship [53].…”

Section: Introductionmentioning

confidence: 99%

Complex conversational scene analysis using wearable sensors

Hung

Gedik

Quiros

2019

Multimodal Behavior Analysis in the Wild

View full text Add to dashboard Cite

“…More recently, other research fields, including emotion recognition, have also started to shift their focus from individual to group settings Mou et al (2016aMou et al ( , 2015. Research works focusing on the analysis of social dimensions, such as engagement and rapport in group settings have also been reported in Leite et al (2015) and Hagad et al (2011). Zhang and Hung (2016) and Vascon et al (2016) propose frameworks for F-formation detection in group conversations.…”

Section: Introductionmentioning

confidence: 99%

“…investigated the individual personality and engagement in dyadic interaction and human-robot interactions Hagad et al (2011). automatically predicted the individual rapport in dyadic interactions based on posture and congruence.…”

mentioning

confidence: 99%

A deep generic to specific recognition model for group membership analysis using non-verbal cues

Mou

Tzelepis

Mezaris

et al. 2019

Image and Vision Computing

View full text Add to dashboard Cite

Automatic understanding and analysis of groups has attracted increasing attention in the vision and multimedia communities in recent years. However, little attention has been paid to the automatic analysis of the non-verbal behaviors and how this can be utilized for analysis of group membership, i.e., recognizing which group each individual is part of. This paper presents a novel Support Vector Machine (SVM) based Deep Specific Recognition Model (DeepSRM) that is learned based on a generic recognition model. The generic recognition model refers to the model trained with data across different conditions, i.e., when people are watching movies of different types. Although the generic recognition model can provide a baseline for the recognition model trained for each specific condition, the different behaviors people exhibit in different conditions limit the recognition performance of the generic model. Therefore, the specific recognition model is proposed for each condition separately and built on top of the generic recognition model. A number of experiments are conducted using a database aiming to study group analysis while each group (i.e., four participants together) were watching a number of long movie segments. Our experimental results show that the proposed deep specific recognition model (44%) outperforms the generic recognition model (26%). The recognition of group membership also indicates that the non-verbal behaviors of individuals within a group share commonalities.

show abstract

Predicting Levels of Rapport in Dyadic Interactions through Automatic Detection of Posture and Posture Congruence

Cited by 15 publications

References 22 publications

Generic to Specific Recognition Models for Membership Analysis in Group Videos

Generic to Specific Recognition Models for Membership Analysis in Group Videos

Complex conversational scene analysis using wearable sensors

A deep generic to specific recognition model for group membership analysis using non-verbal cues

Contact Info

Product

Resources

About