Human Behavior Understanding: Second International Workshop, HBU 2011, Amsterdam, The Netherlands, November 16, 2011. Proceedings

166 Pages·2011·3.71 MB·English

by  Albert Ali Salah

Lecture Notes in Computer Science 7065
CommencedPublicationin1973
FoundingandFormerSeriesEditors:
GerhardGoos,JurisHartmanis,andJanvanLeeuwen
EditorialBoard
DavidHutchison
LancasterUniversity,UK
TakeoKanade
CarnegieMellonUniversity,Pittsburgh,PA,USA
JosefKittler
UniversityofSurrey,Guildford,UK
JonM.Kleinberg
CornellUniversity,Ithaca,NY,USA
AlfredKobsa
UniversityofCalifornia,Irvine,CA,USA
FriedemannMattern
ETHZurich,Switzerland
JohnC.Mitchell
StanfordUniversity,CA,USA
MoniNaor
WeizmannInstituteofScience,Rehovot,Israel
OscarNierstrasz
UniversityofBern,Switzerland
C.PanduRangan
IndianInstituteofTechnology,Madras,India
BernhardSteffen
TUDortmundUniversity,Germany
MadhuSudan
MicrosoftResearch,Cambridge,MA,USA
DemetriTerzopoulos
UniversityofCalifornia,LosAngeles,CA,USA
DougTygar
UniversityofCalifornia,Berkeley,CA,USA
GerhardWeikum
MaxPlanckInstituteforInformatics,Saarbruecken,Germany
Albert Ali Salah Bruno Lepri (Eds.)
Human Behavior
Understanding
Second International Workshop, HBU 2011
Amsterdam,TheNetherlands,November16,2011
Proceedings
1 3
VolumeEditors
AlbertAliSalah
BogaziçiUniversity
DepartmentofComputerEngineering
Bebek34342,Istanbul,Turkey
E-mail:[email protected]
BrunoLepri
FBK-FondazioneBrunoKessler
ViaSommarive18,38100Trento,Italy
E-mail:[email protected]
ISSN0302-9743 e-ISSN1611-3349
ISBN978-3-642-25445-1 e-ISBN978-3-642-25446-8
DOI10.1007/978-3-642-25446-8
SpringerHeidelbergDordrechtLondonNewYork
LibraryofCongressControlNumber:2011941084
CRSubjectClassification(1998):I.5,H.5.2,I.4,I.4.8,I.2,I.2.10,H.3-4
LNCSSublibrary:SL6–ImageProcessing,ComputerVision,PatternRecognition,
andGraphics
©Springer-VerlagBerlinHeidelberg2011
Thisworkissubjecttocopyright.Allrightsarereserved,whetherthewholeorpartofthematerialis
concerned,specificallytherightsoftranslation,reprinting,re-useofillustrations,recitation,broadcasting,
reproductiononmicrofilmsorinanyotherway,andstorageindatabanks.Duplicationofthispublication
orpartsthereofispermittedonlyundertheprovisionsoftheGermanCopyrightLawofSeptember9,1965,
initscurrentversion,andpermissionforusemustalwaysbeobtainedfromSpringer.Violationsareliable
toprosecutionundertheGermanCopyrightLaw.
Theuseofgeneraldescriptivenames,registerednames,trademarks,etc.inthispublicationdoesnotimply,
evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevantprotectivelaws
andregulationsandthereforefreeforgeneraluse.
Typesetting:Camera-readybyauthor,dataconversionbyScientificPublishingServices,Chennai,India
Printedonacid-freepaper
SpringerispartofSpringerScience+BusinessMedia(www.springer.com)
Preface
Automatic computer analysis of humanbehavior is an expanding researcharea,
with many technical challenges and many potential applications, encompass-
ing gaming, surveillance, multimedia, ambient-assisted living, and many more.
TheSecondInternationalWorkshoponHumanBehaviorUnderstanding(HBU)
aimedtobringtogetherresearchersdevelopingandusingcomputeranalysistools
for learning and modeling human behavior, covering both hardware or software
aspects. As such, the topics link areas like pattern recognition, sensor technolo-
gies, social signal processing, and interaction design.
The International Joint Conference on Ambient Intelligence combines con-
cepts of ubiquitous technology, intelligent systems and advanced user interface
design, presenting an excellent opportunity to foster collaborations across dis-
ciplines. The first HBU Workshop had a pattern recognition focus, and was
organized as a satellite to ICPR 2010. The second workshop had a focus theme
on inducing behavioral change, which means moving the computer from a pas-
sive observer role to a socially active participating role and enabling it to drive
some kinds of interaction, such as influencing attitudes and behaviors of people
in natural or virtual environments.
This proceedings volume contains 13 papers presented at the workshop, as
wellastheabstractsofthekeynotetalksbyNuriaOliver(TelefonicaSpain)and
Wijnand Ijsselsteijn (Eindhoven University of Technology), and a summarizing
paper.Wereceived32submissionsintotal,andtheeachpaperwaspeer-reviewed
by at least two members of the Technical ProgramCommittee.
We would like to take the opportunity to thank our Program Committee
membersandreviewersfortheirrigorousfeedback,ourauthorsandourkeynote
speakers for their contributions. We would also like to thank the AmI 2011
Organizing Committee, and in particular Ben Kr¨ose, Gwenn Englebienne, and
Reiner Wichert.
November 2011 Albert Ali Salah
Bruno Lepri
Organization
Conference Co-chairs
Albert Ali Salah Bog˘azi¸ci University, Turkey
Bruno Lepri MIT, USA, and FBK, Italy
Technical Program Committee
Hamid Aghajan Stanford University, USA
Lale Akarun Bo˘gazi¸ci University, Turkey
Oya Aran IDIAP, Switzerland
Mark Cavazza Teesside University, UK
Mauro Cherubini Telefonica Research, Spain
Jeffrey Cohn University of Pittsburgh, USA
Theo Gevers University of Amsterdam, The Netherlands
Jordi Gonza´les Universidad Aut´onoma de Barcelona, Spain
Dirk Heylen University of Twente, The Netherlands
Stephen Intille Northeastern University, USA
Taemie Kim MIT, USA
Tsvika Kuflik University of Haifa, Israel
Bruno Lepri MIT, USA, and FBK, Italy
Vittorio Murino IIT, Italy
Maja Pantic Imperial College London, UK
Eric Pauwels CWI, The Netherlands
Alex Pentland MIT, USA
Fabio Pianesi University of Trento, Italy
Peter Robinson Cambridge University, UK
Michael S. Ryoo ETRI, South Korea
Albert Ali Salah Bog˘azi¸ci University, Turkey
Ben Schouten Eindhoven University of Technology,
The Netherlands
Nicu Sebe University of Trento, Italy
Alessandro Vinciarelli University of Glasgow, UK
Massimo Zancanaro FBK, Italy
Additional Reviewers
Hande Alemdar Leonardo Giusti Hatice Ko¨se
Ne¸se Alyu¨z Jungong Han Ilkka Kosunen
Shlomo Berkovsky Kyriaki Kalimeri Oswald Lanz
Hamdi Dibeklio˘glu Tim van Kasteren Wei Pan
Eyal Dim Cem Keskin
Table of Contents
Human Behavior Understanding for Inducing Behavioral Change:
Application Perspectives.......................................... 1
Albert Ali Salah, Bruno Lepri, Fabio Pianesi, and
Alex Sandy Pentland
Analysis of Human Actions and Activities
Urban Computing and Smart Cities: Opportunities and Challenges in
Modelling Large-Scale Aggregated Human Behavior .................. 16
Nuria Oliver
Human Action Categorization Using Ultrasound Micro-Doppler
Signatures ...................................................... 18
Salvador Dura-Bernal, Guillaume Garreau, Charalambos Andreou,
Andreas Andreou, Julius Georgiou, Thomas Wennekers, and
Susan Denham
Sequential Deep Learning for Human Action Recognition ............. 29
Moez Baccouche, Franck Mamalet, Christian Wolf,
Christophe Garcia, and Atilla Baskurt
One-Sequence Learning of Human Actions .......................... 40
Carlos Orrite, Mario Rodr´ıguez, and Miguel Montan˜´es
Face and Gesture Analysis
Analyzing Facial BehavioralFeatures from Videos.................... 52
Abdenour Hadid
Adaptive Integration of Multiple Cues for Contingency Detection ...... 62
Jinhan Lee, Crystal Chao, Andrea L. Thomaz, and Aaron F. Bobick
DTW Based Clustering to Improve Hand Gesture Recognition......... 72
Cem Keskin, Ali Taylan Cemgil, and Lale Akarun
Persuasive Technologies
Augmenting Social Interactions: Experiments in Socio-emotional
Computing...................................................... 82
Wijnand IJsselsteijn
X Table of Contents
An Energy-SavingSupport System for Office Environments ........... 83
Marc Jentsch, Marco Jahn, Ferry Pramudianto,
Jonathan Simon, and Amro Al-Akkad
From Stress Awareness to Coping Strategies of Medical Staff:
Supporting Reflection on PhysiologicalData......................... 93
Lars Mu¨ller, Vero´nica Rivera-Pelayo, Christine Kunzmann, and
Andreas Schmidt
Why Won’t You Do What’s Good for You? Using Intelligent Support
for Behavior Change ............................................. 104
Michel Klein, Nataliya Mogles, and Arlette van Wissen
A Research Framework for Playful Persuasion Based on Psychological
Needs and Bodily Interaction...................................... 116
Marco Rozendaal, Arnold Vermeeren, Tilde Bekker, and
Huib de Ridder
Social Interactions
Automatic Modeling of Dominance Effects Using Granger Causality.... 124
Kyriaki Kalimeri, Bruno Lepri, Taemie Kim, Fabio Pianesi, and
Alex Sandy Pentland
Abnormal Crowd Behavior Detection by Social Force Optimization..... 134
R. Raghavendra, Alessio Del Bue, Marco Cristani, and
Vittorio Murino
Understanding the Influence of Social Interactions on Individual’s
Behavior Pattern in a Work Environment ........................... 146
Chih-Wei Chen, Asier Aztiria, Somaya Ben Allouch, and
Hamid Aghajan
Author Index.................................................. 159
Human Behavior Understanding for Inducing
Behavioral Change: Application Perspectives
Albert Ali Salah1, Bruno Lepri2,3, Fabio Pianesi2, and Alex Sandy Pentland3
1 Bog˘azi¸ci University,Department of Computer Engineering,
Istanbul, Turkey
[email protected]
2 FBK, via Sommarive 18, Povo,
Trento, Italy
{lepri,pianesi}@fbk.eu
3 MIT Media Lab, 20 Ames Street,02-139 Cambridge,
MA, USA
[email protected]
Abstract. Pervasive sensing and human behavior understanding can
help us in implementing or improving systems that can induce behav-
ioral change. In this introductory paper of the 2nd International Work-
shop onHumanBehaviorUnderstanding(HBU’11), whichhasaspecial
focusthemeof“InducingBehavioralChange”,weprovideataxonomyto
describe where and how HBU technology can be harnessed to this end,
and supply a short survey of the area from an application perspective.
Wealso consider how social signals and settings relate to this concept.
1 Introduction
In recent years, the automatic analysis of human behavior has been attracting
anincreasingamountof attentionfromresearchersbecause ofits importantpo-
tential applications and its intrinsic scientific challenges. In many technological
fields(pervasiveandubiquitouscomputing,multimodalinteraction,ambientas-
sistedlivingandassistedcognition,computersupportedcollaborativework,user
modeling, automatic visual surveillance, etc.) the awareness is emerging that a
systemcanprovidebetter andmoreappropriateservicestopeople only ifitcan
understand much more about users’ attitudes, preferences, personality, social
relationships etc., as well as about what people are doing, the activities they
have been engaged in the past, their routines and life-styles, etc.
At the same time, severalattempts have been made to build persuasive tech-
nologies.Mostoftheresearchonthistopicisoftencomprisedundertheumbrella
oftheterm‘captology’,whichgenerallyreferstothestudyofmachinesdesigned
to influence people’s attitudes and behaviors. The challenge in captology is to
design an engaging and stimulating environment (or technology) that in time
wouldsteertheuser’sbehaviortowardsadesiredbehavior.In[15],Foggstresses
the distinction betweena technology’sside effects andits plannedeffects,where
A.A.SalahandB.Lepri(Eds.):HBU2011,LNCS7065,pp.1–15,2011.
(cid:2)c Springer-VerlagBerlinHeidelberg2011
2 A.A. Salah et al.
the latter is relevant from a design perspective. For instance, exposure to vio-
lent video games may increase aggressivethoughts, feelings, and behaviors,and
decrease helping behavior, as unplanned side effects [2]. Although a better un-
derstanding of the mechanisms underlying side effects would make it possible
to compensate for them, it is the planned effects themselves that have been
attracting most of the attention.
Currenteffortstowardspersuasivetechnologieshaverarelytakenintoaccount
the real-time understandingofindividualtraits orthe socialdynamicsthe users
engagein.Technologiesforhumanbehaviorunderstanding(HBU),however,can
be gainfully employed to make these persuasive systems more context-aware,
interactive, adaptive, immersive and even anthropomorphic. The goal of this
paper is to give an application perspective on how to reach these goals. Since
persuasion is not always an explicit goal of such systems (as we will show later
viaexamples),thesystemswedescribeherespanabroaderareathan“classical”
persuasive technologies.
Thispaperisstructuredasfollows.Section2describestaxonomiesforemploy-
ing HBU in a persuasive environment. Then, Section 3 reports recent research
focusindifferentpervasivesensingmodalities.Section4givesapplicationexam-
ples for inducing behavior change,selected from four different domains. Finally,
Section5 concludesthe paper.Inthis work,we arenotgoingto discussthe the-
oreticaland socialaspects ofbehavioralchange;these are tackledina follow-up
paper explicitly dealing with these issues [34]. In the present volume, [31] gives
a good overview of theories on behavior change.
2 Taxonomies
InthissectionwediscusswhereandhowHBUcanbeemployedtoinducebehav-
ioralchange.Weshouldnoteherethatincomputerscience,theterm“behavior”
usually refers to a relatively short, measurable pattern of activity, whereas in
psychology,it incorporatesa broadrange of details, pertaining to ability, inten-
tions, and sustainability. The construction of relations between different time
scales is one of the challenges in this area. By Human Behavior Understanding
(HBU), we meanhere patternrecognitionandmodeling techniques to automat-
ically interpret complex behavioral patterns generated when humans interact
with machines or with other humans [52]. These patterns encompass actions
and activities, attitudes, affective states, social signals, semantic descriptions,
and contextual properties [53]. Since persuasionis a detailed frameworkfor dis-
cussing how to induce behavior change, we will adopt it as our main guideline,
and deviate from it only occasionally.
Technology can achieve persuasion by being a tool (improving abilities, pro-
vidingcustomizedinformation,guidingpeoplethroughaprocess,etc.),bybeing
the channel of persuasion (particularly relevant for ambient intelligence (AmI)
scenarios,where the environmentuses feedback andvisualizationto providebe-
havior changing experiences) or by being a social actor to persuade through
social communication channels [15].