Real-time motion attention and expressive gesture interfaces

Abstract: This paper aims at investigating the relationship between gestures’ expressivity and the amount of attention they attract. We present a technique for quantifying behavior saliency, here understood as the capacity to capture one’s attention, by the rarity of selected motion and gestural expressive features. This rarity index is based on the real-time computation of the occurrence probability of expressive motion features numerical values. Hence, the time instants that correspond to rare unusual dynamic patterns of an expressive feature are singled out. In a multi-user scenario, the rarity index highlights the person in a group which shows the most different behavior with respect to the others. In a mono-user scenario, the rarity index highlights when the expressive content of a gesture changes. Those methods can be considered as preliminary steps toward context-aware expressive gesture analysis. This work has been partly carried out in the framework of the eNTERFACE 2008 workshop (Paris, France, August 2008) and is partially supported by the EU ICT SAME Project ( and by the NUMEDIART Project (

Keywords: computational attention, saliency, rarity, expressive gesture

Mancas, M., Glowinski, D., Volpe, G., Camurri, A., Coletta, P., Bretéché, P., Demeyer, J., & Ravet, P. (2008). Real-time motion attention and expressive gesture interfaces. Journal on Multimodal User Interfaces, 2(3-4), 187-198. PDF

Technique for automatic emotion recognition by body gesture analysis

Abstract: This paper illustrates our recent work on the analysis of expressive gesture related to the motion of the upper body (the head and the hands) in the context of emotional portrayals performed by professional actors. An experiment is presented which is the result of a multidisciplinary joint work. The experiment aims at (i) developing models and algorithms for analysis of such expressive content (ii) individuating which motion cues are involved in conveying the actorpsilas expressive intentions to portray four emotions (anger, joy, relief, sadness) via a scenario approach. The paper discusses the experiment in detail with reference to related conceptual issues, developed techniques, and the obtained results.

Glowinski, D., Camurri, A., Volpe, G., Dael, N., & Scherer, K. (2008). Technique for automatic emotion recognition by body gesture analysis. In Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference, June (pp. 1-6). PDF

Valutazione degli errori cognitivi da disattenzione

Abstract: Vi sono contesti (e.g., guida di mezzi di trasporto) in cui l’errore umano può comportare costi non trascurabili in termini di efficienza e sicurezza e un ruolo centrale in questo senso è giocato dalla disattenzione. Nel presente studio si è proceduto alla validazione italiana del Attention Related Cognitive Errors (ARCES, Cheyne et al. 2006), un test mirato alla valutazione di errori dovuti all’attenzione sostenuta. Un primo campione di soggetti (N = 119) ha completato una batteria comprendente ARCES, una misura di presenza mentale (Mindful Attention Awareness Scale – MAAS, Warren et al. 2003), il Cognitive Failure Questionnaire (CFQ), (Broadbent et al., 1982; versione italiana di Mecacci et al., 2004), e due questionari per la valutazione della memoria prospettica e/o retrospettiva: Questionario di Autovalutazione della Memoria Prospettica (QMP, Cicogna et al., 1997) e Prospective and Retrospective Memory Questionnaire (PRMQ, Smith et al., 2000); un secondo campione (N = 25) ha completato ARCES, MAAS, Everyday Memory Failure Scale (MFS, Cheyne et al. 2006), CFQ e QMP, insieme al Sustained Attention to Response Task (SART, Robertson et al., 1997), una prova comportamentale che rivela la propensione a commettere errori in compiti di attenzione sostenuta e che fornisce due punteggi: tempo di reazione a stimoli yes-go (SART-RT) e numero di errori (SART-ERR). I risultati mostrano che ARCES possiede adeguate coerenza interna (alpha = .82) e validità di costrutto e di criterio, in quanto il punteggio correla in modo sostanziale (r > |.30|) con tutte le misure impiegate, anche se non con età, genere e scolarità. Da entrambi gli studi emerge che ARCES può essere vantaggiosamente utilizzato per l’indagine di costrutti collegati con l’attenzione (e.g., il carico di lavoro cognitivo) e, quando inserito in una batteria multidimensionale come quella impiegata in questo lavoro, per lo screening nella valutazione degli operatori.

Bracco, F., Chiorri, C., & Vannucci, M. (2007). Valutazione degli errori cognitivi da disattenzione. Comunicazione per il Congresso Nazionale sezione di Psicologia Sperimentale AIP, Como, 17-19 Settembre.  PDF

Validation of an Algorithm for Segmentation of Full-Body Movement Sequences by Perception: A Pilot Experiment

AbstractThis paper presents a pilot experiment for the perceptual validation by human subjects of a motion segmentation algorithm, i.e., an algorithm for automatically segmenting a motion sequence (e.g., a dance fragment) into a collection of pause and motion phases. Perceptual validation of motion and gesture analysis algorithms is an important issue in the development of multimodal interactive systems where human full-body movement and expressive gesture are a major input channel. The discussed experiment is part of a broader research at DIST-InfoMus Lab aiming at investigating the non-verbal mechanisms of communication involving human movement and gesture as primary conveyors of expressive emotional content.

Glowinski, D., Camurri, A., Chiorri, C., Mazzarino, B., & Volpe, G. (2007). Validation of an algorithm for segmentation of full-body movement sequences by perception: A pilot experiment. In M., Sales Dias, M. M., Wanderley, & R., Bastos, (Eds.),  Gesture-based human-computer interaction and simulation (pp. 239-244). Berlin: Springer Heidelberg. PDF

Cognitive ergonomics in High Reliability Organizations

Human cognitive system is the key point in a wider field where technology, psychology and organization meet. Our strength is at the same time our weakness: we are flexible but fallible, instead of machines, less fallible, but more rigid. Cognitive ergonomics emerges as a feasible perspective to face with these issues. Specifically, we point to High Reliability Systems (HRS), i.e. those activities where the cost of a failure is greater than the lesson learned. Perfect examples of HRS are transportations (aircrafts, ships, trains, etc.) and industrial activities (e.g. power plants). The aim of future research is to build a stronger integration among the several actors in HRS, keeping in mind that the human factor is, and has to be, the core of a multidisciplinary approach. As Alan Turing once said: if a machine is expected to be intelligent, it will not be error-free; if it has to be error-free, it will not be intelligent.

Bracco F., Pisano L., Spinelli G. (2005). Cognitive ergonomics in High Reliability Organizations, relazione presso l’International workshop on Human Factors in ship design, Facoltà di Architettura, Università di Genova, 6 ottobre 2005. PDF