To Beat or Not To Beat? Beat Gestures in Direction Giving Chris Brandhorst & Mariët Theune University of Twente.

Slides:



Advertisements
Similar presentations
Ciara R. Wigham, 15 Dec Initiation 1. simple (elementary) 2. complex (episodic, instalment, provisional, dummy, proxy) Refashioning 1. request.
Advertisements

At the conclusion of this presentation, you will… important.  Understand why note taking is important.  Have some viable options for taking notes in.
Cornell Notes.
ORGANIZING THE CONTENT Physical Structure
Why iconic gestures aren’t very iconic
QoS Impact on User Perception and Understanding of Multimedia Video Clips G. Ghinea and J.P. Thomas Department of Computer Science University of Reading,
Getting Started. Edline Web Site Requirements Provide Students and Parents With: 1.A Brief Course Description 2.Your Address 3.Course Syllabus 4.Major.
MCTS GUIDE TO MICROSOFT WINDOWS 7 Chapter 10 Performance Tuning.
Greg Wadley and Nic Ducheneaut 1 The 'Out of Avatar Experience': Collaboration around Objects in Second Life Greg Wadley, Uni of Melbourne + Nic Ducheneaut,
Higher English Close Reading The Final Question Tuesday 8 OctoberCMCM1.
Writing Essays and Reports Notes taken from Jean Rose “The mature students guide to writing,” palgrave study guides.
Unsupervised Clustering in Multimodal Multiparty Meeting Analysis.
CS 501: Software Engineering
Meaningful Learning in an Information Age
DAMN : A Distributed Architecture for Mobile Navigation Julio K. Rosenblatt Presented By: Chris Miles.
Strategies to Promote Motivation in the Mathematics Classroom
Video for Mobile Device Mark Green School of Creative Media.
Understanding Non- Verbal Communication MRS. DOBBINS.
Introduction to Computing By Engr. Bilal Ahmad. Aim of the Lecture  In this Lecture the focus will be on Technology, we will be discussing some specifications.
“The more two speakers have in common, the less language they’ll need to use to identify familiar things”  “Pragmatics” Chapter 2 “Deixis and distance”
Reported Speech Roll No Presented By:- Class: Ixth “A”
Reader’s Theatre What is it? & How do we prepare for a reader’s theatre?
EQ 10: Lifelong Learning By: Marcus Peyton. Part 1: Tools used in the course.
SAT Prep: Improving Paragraphs AVID III Spring 2012.
NEIL H. SCHWARTZ, PH.D. SEMINAR IN COGNITIVE VISUALIZATION Visual vs. Language-based Thinking.
ACT: The Reading Test.
Grade 2 – Module 8 Module Focus Session
Supporting your child with reading.
1 Linguistics lecture #9 November 23, Overview Modularity again How visual cognition affects language How spatial cognition affects language Can.
Microsoft Wang Li, Wang Yini, Li YIcheng.  This is a presentation about Microsoft Windows7 guidelines  Wang Li K8wali00  Li Yicheng K8liyi00  Wang.
MCTS Guide to Microsoft Windows 7
COMPOSITION 9 Parts of Speech: Verbs Action Verbs in General  Follow along on Text page 362.  A verb either expresses an action (what something or.
Chapter 2 Arithmetic Strategies & Area
Common Ground Linguistic referents are established w/in a “domain of interpretation”, which includes context –One component of context = Common Ground.
CS 360 Lecture 3.  The software process is a structured set of activities required to develop a software system.  Fundamental Assumption:  Good software.
Psych 156A/ Ling 150: Psychology of Language Learning Lecture 5 Sounds III.
Chapter 7. BEAT: the Behavior Expression Animation Toolkit
Roger J. Chapman Multimodal Slide Shows as Asynchronous Presentation Reviews The University of Hawaii, at Hilo Computer Science Department.
Detailed design – class design Domain Modeling SE-2030 Dr. Rob Hasker 1 Based on slides written by Dr. Mark L. Hornick Used with permission.
Useful tips © Gerlinde Darlington MEd.Mag.phil..  Introduction  Main part – consisting of a few paragraphs  Conclusion  Remember: poorly structured.
The Writing Section of the SAT Strategies for the Multiple Choice Questions.
Cornell note taking stimulates critical thinking skills. Note taking helps you remember what is said in class. A good set of notes can help you work on.
Giving Oral Presentations
Dynamic Presentation of Key Concepts Module 5 – Part 1 Fundamentals of Operational Amplifiers Filename: DPKC_Mod05_Part01.ppt.
SEG3120 User Interfaces Design and Implementation
N o, you don’t understand, I mean… Irini Nomikou supervisor: Dr. Floriana Grasso The one with the conductor and the girl on the train Cond: Did you pay.
ENTERFACE 08 Project 1 “MultiParty Communication with a Tour Guide ECA” Mid-term presentation August 19th, 2008.
1 Multi-Perspective Question Answering Using the OpQA Corpus (HLT/EMNLP 2005) Veselin Stoyanov Claire Cardie Janyce Wiebe Cornell University University.
Team TFY (Think For You).  Problems we want to solve  What we showed last time  Our new solutions now  Our feature list  Issues identified so far.
Understanding and using patterns in software development EEL 6883 Software Engineering Vol. 1 Chapter 4 pp Presenter: Sorosh Olamaei.
What We Know People Know About Gesture Barbara Kelly and Lauren Gawne University of Melbourne.
AP English Language and Composition Multiple Choice Tips.
Nonverbal Communication. Communication in general is process of sending and receiving messages that enables humans to share knowledge, attitudes, and.
After testing users Compile Data Compile Data Summarize Summarize Analyze Analyze Develop recommendations Develop recommendations Produce final report.
An evolutionary approach for improving the quality of automatic summaries Constantin Orasan Research Group in Computational Linguistics School of Humanities,
Software Development Process CS 360 Lecture 3. Software Process The software process is a structured set of activities required to develop a software.
Executive Summary - Human Factors Heuristic Evaluation 04/18/2014.
IT323 - Software Engineering 2 1 Tutorial 3.  Suggest ways in which the user interface to an e-commerce system such as an online stores might be adapted.
WP6 Emotion in Interaction Embodied Conversational Agents WP6 core task: describe an interactive ECA system with capabilities beyond those of present day.
SurveyDIG 2.1 Tutorial. Tutorial Contents Introduction Introduction Item Groups Item Groups –Creating new Groups –Naming Convention –Searching/Editing.
How to fix Error code 0x80072ee2 in Windows 8.1? Fix%20%20Update%20Error%200x80072EE2%20in%20Windows%20 8.1,%20Windows%2010!%20-%20Fix%20PC%20Errors.htm.
The Multi-agent System for Dynamic Network Routing Ryokichi Onishi The Univ. of Tokyo, Japan.
SurveyDIG 2.1 Tutorial.
Class Conversations: Get into group’s of 5.
Mixed Medium The distinction between the medium of speech and the medium of writing at first seems clear-cut: either things are written or they are spoken.
Manufacturing system design (MSD)
IDEA Student Ratings of Instruction
Know Your Audience: Demographics
Mixed Medium The distinction between the medium of speech and the medium of writing at first seems clear-cut: either things are written or they are spoken.
Presentation transcript:

To Beat or Not To Beat? Beat Gestures in Direction Giving Chris Brandhorst & Mariët Theune University of Twente

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Overview Beats and other gesture types Research context: The Virtual Guide A small direction giving corpus How to recognize beats? The Beat Filter When are beats used? Concept categories A (very) simple beat usage model Conclusions and future work

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Beats and other gestures Gesture types Deictic: pointing at an object’s location Iconic: representing the shape of a concrete object Metaphoric: depicting an abstract object using metaphor Beat: indicating discourse structure; emphasis McNeill (1992) “Hand and Mind” p.93: beats made up 44.7% of used gestures in a cartoon narration corpus.

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Context: The Virtual Guide An embodied direction giving agent in a 3D environment

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Video (link naar filmpje hier) Try out the Virtual Guide “live” here:

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Gesture generation Keyword-based Turns (“left”, “right”, etc.): fixed pointing gesture in turn direction Objects (“the coffee counter”, etc.): –pointing gesture to absolute 3D object location (gesture is computed dynamically) –pointing gesture to relative object location, from viewpoint along the route (fixed gesture; like Turns) –iconic gesture reflecting object shape (fixed gesture from “gestionary”)

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop When to use beat gestures? In the BEAT system (Cassell et al., 2001) gestures are used to mark new information and to contrast items Beats are given low priority: they are only used when no other gesture type is available In the Virtual Guide, in almost all cases a pointing or iconic gesture is available – so, no “need” for beats? No: human direction givers do often use beat gestures, as shown in our small video corpus.

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Direction giving video corpus Used for this study: 15 short video clips (± 45 sec. each) 4 different Dutch speakers, 3-4 clips each 2 different destinations in our building 2 versions of each clip (except one): with a listener present or to the camera 133 gestures; 124 annotated (others not clearly visible)

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop How to recognize beats? Beat characteristics: “A simple flick of the hand” Short and quick Only 2 gesture phases: preparation and retraction (no stroke) No “tensed stasis” Formless hand shape Formal coding, based on shape only: the Beat Filter (McNeill, 1992) “filters out” beats from other gestures.

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop The Beat Filter 1.Does the gesture have other than 2 movement phases? 2.How often does tensed stasis or finger movement appear? 3.If the first movement is in non-center space, is any other movement in center space? 4.If there are exactly 2 movement phases, are they in different spaces? Add 1 point for each “yes” answer to Questions 1, 3, 4 to the number given in answer to Question 2. The lower the score, the more likely the gesture is a beat.

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Using the Beat Filter (1) 109 gestures were scored with the Beat Filter* 95 of those were annotated by two annotators (the other 14 were used as test items) Annotator agreement on the Beat Filter questions was very low: –Question 1: K = 0.43 –Question 2: K = 0.31 –Question 3: K = 0.18 –Question 4: answer is dependent on Q1, so computing reliability makes no sense *15 gestures were considered to be “obvious” (other gesture types than beats) and not “filtered” by annotator A …!

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Using the Beat Filter (2) Agreement on total Beat Filter scores: 44.2% same score (but possibly on different grounds!) 36.8% difference of % difference of 2 2.1% difference of 3 In the end, only the scores of annotator A were used.

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Annotating gesture types Gesture types based on global shape information: resemblance to mentioned object, finger pointing, directional component, etc. (in combination with speech) Annotator agreement: Agreed on 83.3% of gesture types (102 of 124), K=0.73 –Of these, 33.3% are beats (34 of 102) Disagreed on 17.7% of gesture types (22 of 124) –Most confused were point and iconic (45.5%) –Next most confused were beat and point (13.6%)

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Gesture types and beat score Beats do have lower Beat Filter scores Many pointing gestures have low scores too *NF (Not Filtered) gesture types were not entirely obvious after all…! NF*#% beat ‘multi-beat’443.2 iconic point not agreed #

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop When are beat gestures used? Some direction giving concept categories were defined: Directions (up, down, left, right, …) (Other) Spatial information (through, in, on, at, across, …) Duration & Timing (all the way, continue, immediately, …) Landmarks –Nouns (windows, a square, the hallway, …) –Pronouns (that, the same, this, they, it, …) Points in Time or Space (now, then, here, there, …) Hesitations (uh, uhm, I would say, something like that, maybe, …)

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Concepts / gestures overview Concept#Beat (%)Other (%)Total (%) Spatial info456 (13.3%)3 (6.7%)9 (20.0%) Hesitations959 (9.5%)4 (4.2%)13 (13.7%) Duration & timing373 (8.1%)1 (2.7%)4 (10.8%) Landmarks1767 (4.0%)30 (17.0%)37 (21.0%) pronoun493 (6.1%)6 (12.2%)9 (18.3%) noun1274 (3.1%)25 (19.7%)29 (22.8%) Points in time/space1024 (3.9%)12 (11.8%)16 (15.7%) Directions841 (1.2%)39 (46.4%)40 (47.6%) Total53930 (5.6%)89 (16.5%)119 (22.1%) Othern/a4 (n/a)10 (n/a)14 (n/a)

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Concept Categories Relative frequency of concept categories: Landmarks are most frequently mentioned Directions are only in fourth place

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Concepts and gestures Not fitting into these categories: 4 beats, 10 “other gestures” SI = Spatial Information; H = Hesitations; DT = Duration & Timing; L = Landmarks; PTS = Points in Time or Space; D = Directions

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Landmarks: pronoun or noun Landmarks as pronouns: fewer gestures, relatively more beats

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop A simple beat usage model The probability that a beat gesture B is generated to accompany an utterance u (and modelling speaker s): P(B|u) = P(B|C u ) x m s where C u is the concept category of u P(B|C u ) is the probability of B accompanying C u based on corpus data m s is an optional multiplier for speaker s (weight factor)

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Toward a better model Other factors than just corpus frequency should be taken into account. For example: First or second time the same directions are given? Listener present or not? Context: influence of preceding and following concepts / gestures Etc. And of course, more (and more reliable!) corpus data are needed.

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Conclusions How can we recognize beats? Applying Beat Filter to recognize beat gestures may not give reliable results “Impressionistic” gesture type annotation was more reliable Add “directionality” and “hand shape” to Beat Filter? When are beats used? “Other” gestures don’t always take precedence over beats Beats mark spatial information, hesitations, duration and timing more often than other gestures do

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop Future work More data More reliable annotation Investigate when beats or other gestures are used given a concept category Better / more general concept categories? → Implement in the Virtual Guide

Brandhorst & Theune – Beat Gestures in Direction Giving – Gesture Workshop The End Questions?