It is our great pleasure to welcome you to the 2nd International Workshop on Social Signal Processing. The call for papers attracted 21 submissions of very high quality and the program committee accepted 11 papers that cover a variety of topics, including automatic understanding and analysis of nonverbal behavior in social interactions, conceptual modeling of social signals and social behavior, and synthesis of nonverbal behavioral cues. The program includes not only the presentation of the accepted works, but also four prestigious keynote speakers (Justine Cassell, Jeff Cohn, Toyoaki Nishida and Alex Pentland) and a panel discussion as well. We are confident that the proceedings, presentations and discussions will offer an exhaustive idea of the state-ofthe- art in Social Signal Processing.
Like in the first edition of the workshop, we are happy to gather researchers active in a wide variety of domains, from low-level signal processing to cognitive sciences and behavior synthesis. Social Signal Processing is an inherently multidisciplinary domain and progress can emerge only from the cross-pollination between multiple areas. We hope that the workshop will offer ideal conditions for a fruitful and effective exchange between these diverse domains.
Proceeding Downloads
Social signal processing in depression
As social signal processing develops as a field of enquiry and application, there is emerging focus on individual differences in social signaling. My colleagues and I have been particularly interested in social signal processing in depression. ...
Kith and kin: how social networks make us smart
My research shows that the attitudes and actions of peers, rather than logic or argument, usually dominates people's beliefs and actions. The mechanism appears to be based on learning by example from kithmates (a set of peers relevant to the problem at ...
Differences in listener responses between procedural and narrative task
In the long tradition of corpus based research on listener behavior, whether it entails linguistic analysis or social signal processing, many different tasks have been used during the recording of the corpus. So far in no study the task which has been ...
Discriminative space-time voting for joint recognition and localization of actions.
In this paper we address the problem of activity detection in unsegmented image sequences. Our main contribution is the use of an implicit representation of the spatiotemporal shape of the activity which relies on the spatiotemporal localization of ...
The voice of personality: mapping nonverbal vocal behavior into trait attributions
This paper reports preliminary experiments on automatic attribution of personality traits based on nonverbal vocal behavioral cues. In particular, the work shows how prosodic features can be used to predict, with an accuracy up to 75% depending on the ...
Cognitive modelling of human social signals
The paper defines as "social signal" a communicative or informative signal that, either directly or indirectly, conveys information about social actions, social interactions, social emotions, social attitudes and social relationships. It proposes a ...
From observation to interaction
Conversation is a natural and powerful means of communication for people to collaboratively create and share information. People are very fluent both in aligning their behavior with each other and in coordinating multiple modalities to create meaning. A ...
Improving speech processing trough social signals: automatic speaker segmentation of political debates using role based turn-taking patterns
Several recent works on social signals have addressed the problem of statistical modeling of social interaction in multi-party discussions showing that characteristics like turn-taking patterns can be modeled and predicted according to the role that ...
The organisation of floor in meetings and the relation with speaker addressee patterns
We present a procedure for conversational floor annotation and discuss floor types and floor switches in face-to-face meetings and the relation with addressing behavior. It seems that for understanding interactions in meetings an agent needs a layered ...
Causal-modelling of personality traits: extraversion and locus of control
This work contributes to the task of automatically analyzing people's personality during social interaction by using acoustic and visual features. We focus on two personality traits: Extraversion, one of the Big Five dimensions, and the Locus of Control ...
Multimodal coordination: exploring relevant features and measures
The decisive role of interpersonal coordination in social interactions is well established. As human beings, we are "experts" in decoding and producing social signals, learning since our birth. Though, equipping a machine with the same abilities ...
Postural expressions of action tendencies
One of the challenges of virtual character research is the specification of reliable and discriminative features of complex emotions in multiple modalities. Whereas expressions of different emotion categories in facial expressions, gaze, and gestures ...
Implicit image tagging via facial information
Implicit Tagging is the technique to annotate multimedia data based on user's spontaneous nonverbal reactions. In this paper, a study is conducted to test whether user's facial expression can be used to predict the correctness of tags of images. The ...
Towards a smiling ECA: studies on mimicry, timing and types of smiles
Smile is one of the most often used nonverbal signals. Depending on when, how and where it is displayed, it may convey various meanings. We believe that introducing the variety of smiles may improve the communicative skills of embodied conversational ...
Regulative or constitutive behaviors: culture and identity in human interaction
The term 'social signal' implies that one person emits a signal that another picks up, and that the signal regulates some sort of socially appropriate behavior. Taking examples from my recent research on culture and identity both in human-human and ...
- Proceedings of the 2nd international workshop on Social signal processing