Fabrizio Nunnari

Human-Centred Machine Learning

Machine learning is one of the most important and successful techniques in contemporary computer science. It involves the statistical inference of models (such as classifiers) from data. It is often conceived in a very impersonal way, with algorithms working autonomously on passively collected data. However, this viewpoint hides considerable human work of tuning the algorithms, gathering the data, and even deciding what should be modeled in the first place. Examining machine learning from a human-centered perspective includes explicitly recognising this human work, as well as reframing machine learning workflows based on situated human working practices, and exploring the co-adaptation of humans and systems. A human-centered understanding of machine learning in human context can lead not only to more usable machine learning tools, but to new ways of framing learning computationally. This workshop will bring together researchers to discuss these issues and suggest future research questions aimed at creating a human-centered approach to machine learning.

An Avatar-based Interface for the Italian Sign Language

In this paper, we describe a virtual interpreter of the Italian sign language (Italian Sign Language, LIS). developed as part of the on--going ATLAS project, on the automatic translation from Italian to Italian Sign Language. The translation system communicates with the user through a virtual signer: the system takes as input a formal representation of a sign language sentence and produces the corresponding animation of the avatar. The architecture of the virtual signer consists of a resource planner, an executor of the planned sign animations, and an animation system.

Perceiving awareness information through 3D representations

The paper describes a framework supporting the creation of 3D user interfaces to visualize awareness information about the cooperation context of distributed actors. The paper discusses the motivations behind the framework and illustrates ThreeDmap, an editor allowing the creation and customization of 3D interfaces supporting the perception of awareness information.

The canonical processes of a dramatized approach to information presentation

This paper describes the application “Carletto the spider” in terms of the mapping with the canonical processes of media production. “Carletto the spider” is a character-based guide to a historical site and implements the Dramatour approach for the design of drama-based interactive presentations. Dramatization makes presentations more engaging, thus improving the reception of the content by the user. The major technical issue of the approach is the segmentation of the presentation into audiovisual units that are edited on-the-fly in a way that guarantees dramatic continuity while adapting to the user response. We describe the workflow of the application and its mapping to the canonical processes of media production, envisaging possible standardizations for the application portability.

150 Digit. Integrating 3D Visit and Social Functions into a Web 3.0 Learning-Oriented Approach

This paper is about the 150 Digit project, a web 2.0 portal designed for the publicity and dissemination of the exhibitions set up for the celebration of the 150 years of Italian unity. Targeted at schools, 150 Digit encourages the active participation of the users to the classification (in terms of tagging) of the exhibition contents and to the creation of new contents. The social components of the portal are leveraged by a semantic layer, which recommends the users with new tags, thus inducing new connections over the exhibits. Content items are recommended as well using both the same semantic strategy and collaborative filtering approaches. As part of the user involvement, 150 Digit features a 3D visit of the exhibitions, where the users can navigate the reconstruction of the exhibitions through a specifically developed web-plugin.

Towards a model for ubiquitous and mobile computing

The current technological trend depicts a scenario in which space and movement represent aspects that should be considered as first class concepts. Models and conceptualizations are necessary to understand and design ubiquitous systems that are context-aware not just from a technological point of view. The aim of this paper is propose the multilayered multi agent situated system (MMASS) model (which provides an interaction model that is strongly dependant on the spatial structure of the environment) as a conceptual architecture for ubiquitous computing applications. The main contribution of this modelling approach to this domain is to provide a conceptual tool that allows to manage space as a first class concept and to consider in a uniform way both physical and logical spaces. After a brief presentation of the MMASS model, a sample application domain will illustrate how the model can be adopted to specify different aspects that are involved in a ubiquitous system.

Advanced Visual Interfaces for Cultural Heritage

Cultural heritage traditionally draws a lot of research attention when it comes to exploring the potential benefits from application of novel technology in realistic settings. The domain is rich of physical as well as virtual sites objects and infinite information about them. Hence, it is only natural that whenever new technology appears, it is experimented in cultural heritage -- from early dialog systems to state of the art Humanoid robots, eye trackers, virtual/augmented reality devices, and the Internet of Things (IoT). The AVI-CH workshop nicely demonstrate this with the diversity of topics presented by the papers accepted to the workshop.

Toward an intuitive sign language animation authoring system for the deaf

This paper presents an ongoing effort toward an online collaborative framework allowing Deaf individuals to author intelligible signs using a dedicated 3D animation authoring interface. The results that are presented mainly focus on the design of a dedicated user interface assisted by novel input devices. This design cannot only benefit the Deaf but also the linguists studying sign language by providing them with a novel kind of study material. This material would consist of a symbolic representation of intelligible sign language animations together with a fine-grained log of the user’s edit actions. Two user studies demonstrate how Leap Motion and Kinect-like devices can be used together for recording and authoring hand trajectories as well as facial animation.

Exploiting reverse correlation for the generation of virtual characters from personality traits

Judging from appearance, most people assign personality traits to virtual characters. This paper presents a platform capable of generating online Reverse Correlation experiments for studying the relations between the appearance of virtual characters and their assumed personality. The method used by the platform, which leverages crowdsourcing and interactive genetic algorithms, can be used to generate virtual characters starting from a description of their personality. The platform requires a training phase to gather the beliefs and convictions that people have when judging a person from his/her appearance. The method is validated through two experiments. The first experiment provides evidence on how effective the method is in improving the mapping through genetic evolution. The second experiment illustrates how the method relates to the technique of Reverse Correlation to infer which physical attributes contribute to the perception of a specific trait.

Supporting the sense of presence in control environments

This paper proposes a notion of presence which overcomes its strict interpretation in terms of physical projection and perception, and interprets “the sense of being there” as the understanding of “the meaning of what is going on there”. The domain of control environments is considered to illustrate this point and to propose technological solutions combining principles and techniques taken from Artificial Intelligence and Computer Supported Cooperative Work to enhance the interpretation and cooperation capabilities of the involved actors.