Massimo Zancanaro
Bruno Lepri
ABSTRACT
In this paper, we discuss a machine learning approach to automatically detect functional roles played by participants in a face to face interaction. We shortly introduce the coding scheme we used to classify the roles of the group members and the corpus we collected to assess the coding scheme reliability as well as to train statistical systems for automatic recognition of roles. We then discuss a machine learning approach based on multi-class SVM to automatically detect such roles by employing simple features of the visual and acoustical scene. The effectiveness of the classification is better than the chosen baselines and although the results are not yet good enough for a real application, they demonstrate the feasibility of the task of detecting group functional roles in face to face interactions.
- Bales, R. F. Personality and interpersonal behavior. New York: Holt, Rinehart and Winston, 1970.]]Google Scholar
- Banerjee, S. and Rudnicky, A. I. Using Simple Speech-Based Features to Detect the State of a Meeting and the Roles of the Meeting Participants. In Proceedings of the 8th International Conference on Spoken Language Processing (Interspeech 2004-ICSLP), Jeju Island, Korea, October 2004.]]Google Scholar
- Benne, K. D., Sheats, P. Functional Roles of Group Members. In Journal of Social Issues 4, pp. 41--49, 1948.]]Google Scholar
- Bloom, G., Castagna, C. and Warren, B. More than mentors: Principal coaching. Leadership. May/June 2003.]]Google Scholar
- Boud, D., Keogh, R. and Walker, D. (eds.) Reflection: Turning experience into learning. Logan: Kogan Page, 1988.]]Google Scholar
- Brdiczka, O., Maisonnasse, J. and Reignier, P. Automatic Detection of Interaction Groups. In Proceedings of the 7th International Conference on Multimodal Interface. Trento, Italy, October 2005.]] Google ScholarDigital Library
- Carli, G., Gretter, G. A Start-End Point Detection Algorithm for a Real-Time Acoustic Front-End based on DSP32C VME Board. In Proceedings of ICSPAT, Boston, USA. 1992.]]Google Scholar
- Chippendale P. 7th International Conference on Automatic Face and Gesture Recognition - FG2006 (IEEE) Southampton, UK, April 2006.]]Google Scholar
- Cristianini N. and Shawe-Taylor J. Support Vector Machines and other kernel-based learning methods. Cambridge University Press, Cambridge, 2000.]] Google ScholarDigital Library
- Dietterich T. G. Machine Learning for Sequential Data: A Review. In T. Caelli (ed.) Lectures Notes in Computer Science. Springer-Verlag, 2002.]] Google ScholarDigital Library
- Doyle M. and Straus D. How To Make Meetings Work. The Berkley Publishing Group, New York, NY. 1993.]]Google Scholar
- Hall, J. W., Watson, W. H. (1970) The Effects of a normative intervention on group decision-making performance. In Human Relations, 23(4), 299--317.]]Google Scholar
- Hsu C.-W. and Lin C.-J. A Comparison of Methods for Multi-Class Support Vector Machines. In IEEE Transactions on Neural Networks, 13, pp.415--425, 2002.]]Google ScholarDigital Library
- Katz, D., and Kahn, R. L. The Social Psychology of Organizations (2nd ed.) New York: John Wiley, 1978.]]Google Scholar
- Kressel U. Pairwise classification and support vector machines. In B. Scholkopf, C. J. C. Burges and A. J. Smola (eds.) Advances in Kernel Methods -- Support Vector Learning. MIT Press, Cambridge, MA. 1999.]] Google ScholarDigital Library
- McCowan I., Bengio S., Gatica-Perez D., Lathoud G., Barnard M., and Zhang D. Automatic Analysis of Multimodal Group Actions in Meetings. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 27 (3), pp. 305--317, 2005.]] Google ScholarDigital Library
- Oviatt, S. Multimodal Interfaces. In Handbook of Human-Computer Interaction, (ed. by J. Jacko & A. Sears), Lawrence Erlbaum: New Jersey, 2002.]]Google ScholarDigital Library
- Falcon V., Leonardi C., Not E., Pianesi F. and Zancanaro M. Observing Multimodal Behaviour to support Group Dynamics. In Workshop on User-centred Design and Evaluation of Services for Human-Human Communication and Collaboration held in conjunction with ICMI'05. Trento, Italy. October, 2005.]]Google Scholar
- Pianesi, F. Zancanaro M., Falcon V., Not E. Toward Supporting Group Dynamics. In Proceedings of Artificial Intelligence Applications and Innovations. Athens, Greece. June 2006.]]Google Scholar
- Rienks R. and Heylen D. Dominance Detection in Meetings Using Easily Obtainable Features. In Revised Selected Papers of the 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms. Edinbourgh, Scotland, October 2006.]] Google ScholarDigital Library
- Salazar, A. An Analysis of the Development and Evolution of Roles in the Small Group. Small Group Research, 27, 4, pp. 475--503, 1996.]]Google ScholarCross Ref
- Yang Y. A Study on Thresholding Strategies for Text Categorization. Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'01), pp 137--145, 2001.]] Google ScholarDigital Library
Index Terms
- Automatic detection of group functional roles in face to face interactions
Recommendations
Using the influence model to recognize functional roles in meetings
ICMI '07: Proceedings of the 9th international conference on Multimodal interfacesIn this paper, an influence model is used to recognize functional roles played during meetings. Previous works on the same corpus demonstrated a high recognition accuracy using SVMs with RBF kernels. In this paper, we discuss the problems of that ...
Face detection in gray scale images using locally linear embeddings
The problem of face detection remains challenging because faces are non-rigid objects that have a high degree of variability with respect to head rotation, illumination, facial expression, occlusion, and aging. This paper employs a novel technique, ...
Face recognition: component-based versus global approaches
Special issue on Face recognitionWe present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first locate facial components, extract them, and combine them into a single ...
Comments