Virtual agents are increasingly being integrated in our everyday life thanks to their communicative skills and abilities to express social affects like emotions and attitudes. The goal of this work is to evaluate the perception of agents expressing interpersonal attitudes through non-verbal behaviors. The interpretation of these behaviors depends on how they are sequenced and coordinated over time. To encompass the sequentiality and the dynamics of non-verbal signals, we rely on temporal sequence mining. From a multimodal corpus, this algorithm produces meaningful sequences resulting in more adapted expression of social attitudes of the agent.
{"title":"Attitude Modeling for Virtual Character Based on Temporal Sequence Mining: Extraction and Evaluation","authors":"Soumia Dermouche, C. Pelachaud","doi":"10.1145/3212721.3212806","DOIUrl":"https://doi.org/10.1145/3212721.3212806","url":null,"abstract":"Virtual agents are increasingly being integrated in our everyday life thanks to their communicative skills and abilities to express social affects like emotions and attitudes. The goal of this work is to evaluate the perception of agents expressing interpersonal attitudes through non-verbal behaviors. The interpretation of these behaviors depends on how they are sequenced and coordinated over time. To encompass the sequentiality and the dynamics of non-verbal signals, we rely on temporal sequence mining. From a multimodal corpus, this algorithm produces meaningful sequences resulting in more adapted expression of social attitudes of the agent.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114329977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Camurri, G. Volpe, Stefano Piana, M. Mancini, Paolo Alborno, Simone Ghisio
This abstract presents a computational model and a software library for the EyesWeb XMI platform to measure a mid-level movement quality of particular importance to convey expressivity: Postural Tension. A whole body posture can be described by a vector containing the angles between the adjacent lines identifying feet (the line connecting the barycentre of each foot), knees, hip, trunk, shoulders, head, and gaze (eyes direction). Postural Tension is the extent at which a movement exhibits rotation of these multiple horizontal planes including spirals. The abstract presents a definition of this mid-level quality, and describe a demonstration: movement of a user is captured with a low-cost wearable device, postural tension and transmission of energy through the body are then extracted, visualized and sonified.
{"title":"The Energy Lift: automated measurement of postural tension and energy transmission","authors":"A. Camurri, G. Volpe, Stefano Piana, M. Mancini, Paolo Alborno, Simone Ghisio","doi":"10.1145/3212721.3212887","DOIUrl":"https://doi.org/10.1145/3212721.3212887","url":null,"abstract":"This abstract presents a computational model and a software library for the EyesWeb XMI platform to measure a mid-level movement quality of particular importance to convey expressivity: Postural Tension. A whole body posture can be described by a vector containing the angles between the adjacent lines identifying feet (the line connecting the barycentre of each foot), knees, hip, trunk, shoulders, head, and gaze (eyes direction). Postural Tension is the extent at which a movement exhibits rotation of these multiple horizontal planes including spirals. The abstract presents a definition of this mid-level quality, and describe a demonstration: movement of a user is captured with a low-cost wearable device, postural tension and transmission of energy through the body are then extracted, visualized and sonified.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128005275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Radoslaw Niewiadomski, Léa A S Chauvigné, M. Mancini, A. Camurri
In this paper, we propose a set of algorithms to compute the cues of the nonverbal leadership in an unstructured joint full-body physical activity, i.e., the joint activity of two or more interacting persons who perform some movements without a predefined sequence and without a predefined leader. An example of such activity can be a contact dance improvisation. The paper is composed of three parts: cue set, dataset and algorithms. First, we propose a cue set of nonverbal leadership which is grounded on existing literature and studies. It is composed of eight cues that characterize the nonverbal behaviors of the leader in a joint full-body physical activity. In this paper we also introduce a new dataset. It consists of multimodal data (video, MoCap) of contact dance improvisations. Additionally, sensory deprivation conditions (vision and/or touch restraint) were introduced to collect the evidences of the various strategies used by leaders and followers during improvisation. The dataset was annotated by twenty-seven persons who carried out continuous annotation of leadership in the recorded material. In the last part of the paper, we propose a set of algorithms that works on positional 3D data (i.e., joints' positions obtained from motion capture data of dancers). Each algorithm models one among the discussed cues of the nonverbal leadership.
{"title":"Towards a model of nonverbal leadership in unstructured joint physical activity","authors":"Radoslaw Niewiadomski, Léa A S Chauvigné, M. Mancini, A. Camurri","doi":"10.1145/3212721.3212816","DOIUrl":"https://doi.org/10.1145/3212721.3212816","url":null,"abstract":"In this paper, we propose a set of algorithms to compute the cues of the nonverbal leadership in an unstructured joint full-body physical activity, i.e., the joint activity of two or more interacting persons who perform some movements without a predefined sequence and without a predefined leader. An example of such activity can be a contact dance improvisation. The paper is composed of three parts: cue set, dataset and algorithms. First, we propose a cue set of nonverbal leadership which is grounded on existing literature and studies. It is composed of eight cues that characterize the nonverbal behaviors of the leader in a joint full-body physical activity. In this paper we also introduce a new dataset. It consists of multimodal data (video, MoCap) of contact dance improvisations. Additionally, sensory deprivation conditions (vision and/or touch restraint) were introduced to collect the evidences of the various strategies used by leaders and followers during improvisation. The dataset was annotated by twenty-seven persons who carried out continuous annotation of leadership in the recorded material. In the last part of the paper, we propose a set of algorithms that works on positional 3D data (i.e., joints' positions obtained from motion capture data of dancers). Each algorithm models one among the discussed cues of the nonverbal leadership.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125706273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Analyzing and documenting contemporary dance movement data has proven to be a very difficult task due to the vast existence of styles and aesthetics which are characteristic of each individual choreographer. Indeed, identifying movement qualities with the intention of co-relating them to specific meanings and choreographic intentions is practically impossible without taking an artist-driven approach. Moreover, equipping dancers with wearable technology in order to accurately track each of their movements is only applicable in controlled laboratory scenarios, therefore not being a viable approach to analyze large scale real-world rehearsals or performances. This paper describes a visualization system that exposes movement qualities for dance through rendering effects. Combining optical flow analysis with depth video information, we were able to estimate the three-dimensional flow for each point in the cloud. This information was used to color point cloud videos with this information, showing potential to be used for the creation of different rendering effects, which are also discussed in this paper. The data used was captured in a non-intrusive manner during the creation process of a dance piece by Portuguese choreographer Rui Lopes Graça, enabling us to examine nuances and details of the rehearsals' process, which would not be replicable in a laboratory environment.
{"title":"Three-Dimensional Visualization of Movement Qualities in Contemporary Dance","authors":"R. K. D. Anjos, C. Ribeiro, Carla Fernandes","doi":"10.1145/3212721.3212812","DOIUrl":"https://doi.org/10.1145/3212721.3212812","url":null,"abstract":"Analyzing and documenting contemporary dance movement data has proven to be a very difficult task due to the vast existence of styles and aesthetics which are characteristic of each individual choreographer. Indeed, identifying movement qualities with the intention of co-relating them to specific meanings and choreographic intentions is practically impossible without taking an artist-driven approach. Moreover, equipping dancers with wearable technology in order to accurately track each of their movements is only applicable in controlled laboratory scenarios, therefore not being a viable approach to analyze large scale real-world rehearsals or performances. This paper describes a visualization system that exposes movement qualities for dance through rendering effects. Combining optical flow analysis with depth video information, we were able to estimate the three-dimensional flow for each point in the cloud. This information was used to color point cloud videos with this information, showing potential to be used for the creation of different rendering effects, which are also discussed in this paper. The data used was captured in a non-intrusive manner during the creation process of a dance piece by Portuguese choreographer Rui Lopes Graça, enabling us to examine nuances and details of the rehearsals' process, which would not be replicable in a laboratory environment.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134122323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 5th International Conference on Movement and Computing","authors":"","doi":"10.1145/3212721","DOIUrl":"https://doi.org/10.1145/3212721","url":null,"abstract":"","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115416682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rosella P. Galindo Esparza, P. Healey, L. Weaver, Matthew Delbridge
This paper describes an interactive scenography designed to enhance the use of embodied imagination in a stroke survivors' performance workshop called The Green Screening workshop, conceived by the company Split Britches. We explore performance techniques combined with live motion capture to provide participants with an abstract visual world that helps them to enact fantasy scenes they create in front of an audience. A simple interface provides real-time visualisations of participant's body movements in three different scenarios and promotes engagement with the co-present audience. The system was evaluated in two workshops with stroke survivors. The results indicate that the system is effective in encouraging participants' creative use of embodied improvisation.
{"title":"Augmented Embodiment: Developing Interactive Technology for Stroke Survivors","authors":"Rosella P. Galindo Esparza, P. Healey, L. Weaver, Matthew Delbridge","doi":"10.1145/3212721.3212845","DOIUrl":"https://doi.org/10.1145/3212721.3212845","url":null,"abstract":"This paper describes an interactive scenography designed to enhance the use of embodied imagination in a stroke survivors' performance workshop called The Green Screening workshop, conceived by the company Split Britches. We explore performance techniques combined with live motion capture to provide participants with an abstract visual world that helps them to enact fantasy scenes they create in front of an audience. A simple interface provides real-time visualisations of participant's body movements in three different scenarios and promotes engagement with the co-present audience. The system was evaluated in two workshops with stroke survivors. The results indicate that the system is effective in encouraging participants' creative use of embodied improvisation.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116306778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Head movements of groups of participants moving to music allowing for both duple and triple subdivisions were analysed using Recurrence Quantification Analysis. As expected the maximum recurrence rate varied between participant, position in the music, and between groups. The lags of maximum recurrence were only partly corresponding to the metrical levels of the music and syncopated sections confused participants so that they moved to 4/4 rather than 6/8.
{"title":"Rhythmic recurrency in dance to music with ambiguous meter","authors":"S. Dahl, G. Sioros","doi":"10.1145/3212721.3212885","DOIUrl":"https://doi.org/10.1145/3212721.3212885","url":null,"abstract":"Head movements of groups of participants moving to music allowing for both duple and triple subdivisions were analysed using Recurrence Quantification Analysis. As expected the maximum recurrence rate varied between participant, position in the music, and between groups. The lags of maximum recurrence were only partly corresponding to the metrical levels of the music and syncopated sections confused participants so that they moved to 4/4 rather than 6/8.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123592831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents the concept design of an interactive costume for contemporary dance projects. The costume can be configured and cued remotely through a graphical user interface providing the ability to connect to any other stage technologies via OSC or to work in standalone mode. The concept further contributes to integrate IMUs as motion sensors and vibration motors as motion actuators for exploring interactivity of dance movements. Its fashion design is characterized by the aesthetics of illuminated fiber optic cables distributed over the whole performing body but almost invisible when turned off. The presented concept design is part of a larger research project and a performance with such a costume prototype is currently realized and tested for stage environments, in close collaboration with dancer/choreographer, visual artists, and sound composer.
{"title":"Designing a Remote-Controlled Interactive Dance Costume","authors":"Michaela Honauer","doi":"10.1145/3212721.3212879","DOIUrl":"https://doi.org/10.1145/3212721.3212879","url":null,"abstract":"This paper presents the concept design of an interactive costume for contemporary dance projects. The costume can be configured and cued remotely through a graphical user interface providing the ability to connect to any other stage technologies via OSC or to work in standalone mode. The concept further contributes to integrate IMUs as motion sensors and vibration motors as motion actuators for exploring interactivity of dance movements. Its fashion design is characterized by the aesthetics of illuminated fiber optic cables distributed over the whole performing body but almost invisible when turned off. The presented concept design is part of a larger research project and a performance with such a costume prototype is currently realized and tested for stage environments, in close collaboration with dancer/choreographer, visual artists, and sound composer.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125412236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Tajadura-Jiménez, F. Cuadrado, Patricia Rick, N. Bianchi-Berthouze, Aneesha Singh, A. Väljamäe, Frédéric Bevilacqua
People, through their bodily actions, engage in sensorimotor loops that connect them to the world and to their own bodies. People's brains integrate the incoming sensory information to form mental representations of their body appearance and capabilities. Technology provides exceptional opportunities to tweak sensorimotor loops and provide people with different experiences of their bodies. We recently showed that real-time sound feedback on one's movement (sonic avatar) can be used for sensory alteration of people's body perception, and in turn provoke enhanced motor behaviour, confidence and motivation for physical activity (PA) in people while increasing their positive emotions towards their own bodies. Here we describe the design process of a wearable prototype that aims to investigate how we can overcome known body-perception-related psychological barriers to PA by employing action-sound loops. The prototype consists of sensors that capture people's bodily actions and a gesture-sound palette that allows different action-sound mappings. Grounded in neuroscientific, clinical and sports psychology studies on body perception and PA, the ultimate design aim is to enhance PA in inactive populations by provoking changes on their bodily experience.
{"title":"Designing a gesture-sound wearable system to motivate physical activity by altering body perception","authors":"A. Tajadura-Jiménez, F. Cuadrado, Patricia Rick, N. Bianchi-Berthouze, Aneesha Singh, A. Väljamäe, Frédéric Bevilacqua","doi":"10.1145/3212721.3212877","DOIUrl":"https://doi.org/10.1145/3212721.3212877","url":null,"abstract":"People, through their bodily actions, engage in sensorimotor loops that connect them to the world and to their own bodies. People's brains integrate the incoming sensory information to form mental representations of their body appearance and capabilities. Technology provides exceptional opportunities to tweak sensorimotor loops and provide people with different experiences of their bodies. We recently showed that real-time sound feedback on one's movement (sonic avatar) can be used for sensory alteration of people's body perception, and in turn provoke enhanced motor behaviour, confidence and motivation for physical activity (PA) in people while increasing their positive emotions towards their own bodies. Here we describe the design process of a wearable prototype that aims to investigate how we can overcome known body-perception-related psychological barriers to PA by employing action-sound loops. The prototype consists of sensors that capture people's bodily actions and a gesture-sound palette that allows different action-sound mappings. Grounded in neuroscientific, clinical and sports psychology studies on body perception and PA, the ultimate design aim is to enhance PA in inactive populations by provoking changes on their bodily experience.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125569280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We examined the relationship of temporal parameters, tempo and rhythm, to the perceived emotion of audience from viewing a dance. This is a problem of how choreographers manipulate the temporal parameters to express the aesthetic adequately. We conducted a psychophysical categorization task to reveal the relationship between temporal parameters of dance and subjects' subjective appreciation. Our goal was to find a distinctive point of temporal parameters that affect subjects' emotional transition, from positive to negative, vice versa. Subjects categorized dance stimuli in different combinations of tempo and rhythm by performing the two-alternative forced choice task. The results found that subjective interpretation of dance was mainly affected by the tempo, not rhythm. Rhythm had much less impact on the appreciation of affective body expression.
{"title":"Interactive Effect of Tempo and Rhythm on the Emotional Perception of Dance Movements","authors":"Jeehyun Joung, Jeounghoon Kim","doi":"10.1145/3212721.3212844","DOIUrl":"https://doi.org/10.1145/3212721.3212844","url":null,"abstract":"We examined the relationship of temporal parameters, tempo and rhythm, to the perceived emotion of audience from viewing a dance. This is a problem of how choreographers manipulate the temporal parameters to express the aesthetic adequately. We conducted a psychophysical categorization task to reveal the relationship between temporal parameters of dance and subjects' subjective appreciation. Our goal was to find a distinctive point of temporal parameters that affect subjects' emotional transition, from positive to negative, vice versa. Subjects categorized dance stimuli in different combinations of tempo and rhythm by performing the two-alternative forced choice task. The results found that subjective interpretation of dance was mainly affected by the tempo, not rhythm. Rhythm had much less impact on the appreciation of affective body expression.","PeriodicalId":330867,"journal":{"name":"Proceedings of the 5th International Conference on Movement and Computing","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114485236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：