Human-Centred Machine Learning
Workshop Summaries
/
Gillies, Marco
/
Fiebrink, Rebecca
/
Tanaka, Atau
/
Garcia, Jérémie
/
Bevilacqua, Frédéric
/
Heloir, Alexis
/
Nunnari, Fabrizio
/
Mackay, Wendy
/
Amershi, Saleema
/
Lee, Bongshin
/
d'Alessandro, Nicolas
/
Tilmanne, Joëlle
/
Kulesza, Todd
/
Caramiaux, Baptiste
Extended Abstracts of the ACM CHI'16 Conference on Human Factors in
Computing Systems
2016-05-07
v.2
p.3558-3565
© Copyright 2016 ACM
Summary: 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.
Emotional and Functional Challenge in Core and Avant-garde Games
Notes! Notes! Notes!
/
Cole, Tom
/
Cairns, Paul
/
Gillies, Marco
Proceedings of the 2015 ACM SIGCHI Annual Symposium on Computer-Human
Interaction in Play
2015-10-05
p.121-126
© Copyright 2015 ACM
Summary: Digital games are a wide, diverse and fast developing art form, and it is
important to analyse games that are pushing the medium forward to see what
design lessons can be learned. However, there are no established criteria to
determine which games show these more progressive qualities.
Grounded theory methodology was used to analyse language used in games
reviews by critics of both 'core gamer' titles and those titles with more
avant-garde properties. This showed there were two kinds of challenge being
discussed -- emotional and functional which appear to be, at least partially,
mutually exclusive. Reviews of 'core' and 'avant-garde' games had different
measures of purchase value, primary emotions, and modalities of language used
to discuss the role of audiovisual qualities. Emotional challenge, ambiguity
and solitude are suggested as useful devices for eliciting emotion from the
player and for use in developing more 'avant-garde' games, as well as providing
a basis for further lines of inquiry.
Applying the CASSM Framework to Improving End User Debugging of Interactive
Machine Learning
Interactive Machine Learning / Decision Making / Topic Modeling / Robotics
/
Gillies, Marco
/
Kleinsmith, Andrea
/
Brenton, Harry
Proceedings of the 2015 International Conference on Intelligent User
Interfaces
2015-03-29
v.1
p.181-185
© Copyright 2015 ACM
Summary: This paper presents an application of the CASSM (Concept-based Analysis of
Surface and Structural Misfits) framework to interactive machine learning for a
bodily interaction domain. We developed software to enable end users to design
full body interaction games involving interaction with a virtual character. The
software used a machine learning algorithm to classify postures as based on
examples provided by users. A longitudinal study showed that training the
algorithm was straightforward, but that debugging errors was very challenging.
A CASSM analysis showed that there were fundamental mismatches between the
users concepts and the working of the learning system. This resulted in a new
design in which aimed to better align both the learning algorithm and user
interface with users' concepts. This work provides and example of how HCI
methods can be applied to machine learning in order to improve its usability
and provide new insights into its use.
Fluid gesture interaction design: Applications of continuous recognition for
the design of modern gestural interfaces
/
Zamborlin, Bruno
/
Bevilacqua, Frederic
/
Gillies, Marco
/
D'Inverno, Mark
ACM Transactions on Interactive Intelligent Systems
2014-01
v.3
n.4
p.22
© Copyright 2014 ACM
Summary: This article presents Gesture Interaction DEsigner (GIDE), an innovative
application for gesture recognition. Instead of recognizing gestures only after
they have been entirely completed, as happens in classic gesture recognition
systems, GIDE exploits the full potential of gestural interaction by tracking
gestures continuously and synchronously, allowing users to both control the
target application moment to moment and also receive immediate and synchronous
feedback about system recognition states. By this means, they quickly learn how
to interact with the system in order to develop better performances.
Furthermore, rather than learning the predefined gestures of others, GIDE
allows users to design their own gestures, making interaction more natural and
also allowing the applications to be tailored by users' specific needs. We
describe our system that demonstrates these new qualities -- that combine to
provide fluid gesture interaction design -- through evaluations with a range of
performers and artists.
Customizing by doing for responsive video game characters
/
Kleinsmith, Andrea
/
Gillies, Marco
International Journal of Human-Computer Studies
2013-07
v.71
n.7/8
p.775-784
Keywords: Interactive machine learning
Keywords: Embodied design
Keywords: Body expressions
Keywords: Video game characters
© Copyright 2013 Elsevier Ltd.
Summary: This paper presents a game in which players can customize the behavior of
their characters using their own movements while playing the game. Players'
movements are recorded with a motion capture system. The player then labels the
movements and uses them as input to a machine learning algorithm that generates
a responsive behavior model. This interface supports a more embodied approach
to character design that we call "Customizing by Doing'. We present a user
study which shows that using their own movements made the users feel more
engaged with the game and the design process, due in large part to a feeling of
personal ownership of the movement.
Exploring choreographers' conceptions of motion capture for full body
interaction
Full body interaction
/
Gillies, Marco
/
Worgan, Max
/
Peppe, Hestia
/
Robinson, Will
/
Kov, Nina
Proceedings of the 25th BCS Conference on Human-Computer Interaction
2011-07-04
p.205-210
© Copyright 2011 Authors
Summary: We present the results of a group interview of choreographers aimed at
understanding their conceptions of how movement can be used to in live
performance. This understanding intended to inform research into full body
interaction for live performance and other more general full body interfaces.
The results of the interview suggest a new way of conceiving of interaction
with digital technology, neither as a representation of movement, not as an
interface that responds to movement but as a means of transforming movement.
This transformed movement can then serve as a starting point for a dancers
responses to transformations of their own movement thus setting up an
improvisational feedback loop.
Piavca: a framework for heterogeneous interactions with virtual characters
/
Gillies, Marco
/
Pan, Xueni
/
Slater, Mel
Virtual Reality
2010-12
v.14
n.4
p.221-228
Copyright © 2010 Springer
Summary: This paper presents a virtual character animation system for real-time
multimodal interaction in an immersive virtual reality setting. Human to human
interaction is highly multimodal, involving features such as verbal language,
tone of voice, facial expression, gestures and gaze. This multimodality means
that, in order to simulate social interaction, our characters must be able to
handle many different types of interaction and many different types of
animation, simultaneously. Our system is based on a model of animation that
represents different types of animations as instantiations of an abstract
function representation. This makes it easy to combine different types of
animation. It also encourages the creation of behavior out of basic building
blocks, making it easy to create and configure new behaviors for novel
situations. The model has been implemented in Piavca, an open source character
animation system.
EMMA: an automated intelligent actor in e-drama
Short papers
/
Zhang, Li
/
Gillies, Marco
/
Barnden, John
Proceedings of the 2008 International Conference on Intelligent User
Interfaces
2008-01-13
p.409-412
© Copyright 2008 ACM
Summary: We report work on adding an improvisational AI actor and 3D emotional
animation to an existing edrama program, a system for dramatic improvisation in
simple virtual scenarios. The improvisational AI actor has an affect-detection
component, aimed at detecting affective aspects of human-controlled characters'
textual input. It also makes an appropriate response to stimulate the
improvisation based on this affective understanding. A distinctive feature of
our work is a focus on the metaphorical ways in which affect is conveyed.
Moreover, we have also introduced how the detected affective states activate
the animation engine to produce emotional gestures for human-controlled
characters. Finally, we report user testing conducted for the AI actor. Our
work contributes to the conference themes on affective user interfaces, natural
language processing and emotionally believable gesture generation.
Applying Direct Manipulation Interfaces to Customizing Player Character
Behaviour
Authoring Tools 1
/
Gillies, Marco
Proceedings of the 2006 International Conference on Entertainment Computing
2006-09-20
p.175-186
© Copyright 2006 IFIP
Summary: The ability customize a players avatar (their graphical representation) is
one of the most popular features of online games and graphical chat
environments. Though customizing appearance is a common ability in most games,
creating tools for customizing a character's behaviour is still a difficult
problem. We propose a methodology, based on direct manipulation, that allows
players to specify the type of behaviour they would like in a given context.
This methodology is iterative, with the player performing a number of different
customizations in different contexts. Players are also able to continue
customizing their character during play, with commands that can have long term
and permanent effects.
