Extreme Computational Photography
Opening Keynote Address
/
Raskar, Ramesh
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.1
Keywords: femto photography, retinal imaging, 3D displays, lightfield
© Copyright 2015 ACM
Summary: The Camera Culture Group at the MIT Media Lab aims to create a new class of
imaging platforms. This talk will discuss three tracks of research: femto
photography, retinal imaging, and 3D displays. Femto Photography consists of
femtosecond laser illumination, picosecond-accurate detectors and mathematical
reconstruction techniques allowing researchers to visualize propagation of
light. Direct recording of reflected or scattered light at such a frame rate
with sufficient brightness is nearly impossible. Using an indirect
'stroboscopic' method that records millions of repeated measurements by careful
scanning in time and viewpoints we can rearrange the data to create a 'movie'
of a nanosecond long event. Femto photography and a new generation of
nano-photography (using ToF cameras) allow powerful inference with computer
vision in presence of scattering. EyeNetra is a mobile phone attachment that
allows users to test their own eyesight. The device reveals corrective measures
thus bringing vision to billions of people who would not have had access
otherwise. Another project, eyeMITRA, is a mobile retinal imaging solution that
brings retinal exams to the realm of routine care, by lowering the cost of the
imaging device to a 10th of its current cost and integrating the device with
image analysis software and predictive analytics. This provides early detection
of Diabetic Retinopathy that can change the arc of growth of the world's
largest cause of blindness. Finally the talk will describe novel lightfield
cameras and lightfield displays that require a compressive optical architecture
to deal with high bandwidth requirements of 4D signals.
GelTouch: Localized Tactile Feedback Through Thin, Programmable Gel
Session 1A: Tactile Feedback
/
Miruchna, Viktor
/
Walter, Robert
/
Lindlbauer, David
/
Lehmann, Maren
/
von Klitzing, Regine
/
Müller, Jörg
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.3-10
© Copyright 2015 ACM
Summary: We present GelTouch, a gel-based layer that can selectively transition
between soft and stiff to provide tactile multi-touch feedback. It is flexible,
transparent when not activated, and contains no mechanical, electromagnetic, or
hydraulic components, resulting in a compact form factor (a 2mm thin
touchscreen layer for our prototype). The activated areas can be morphed freely
and continuously, without being limited to fixed, predefined shapes. GelTouch
consists of a poly(N-isopropylacrylamide) gel layer which alters its
viscoelasticity when activated by applying heat (>32°C). We present
three different activation techniques: 1) Indium Tin Oxide (ITO) as a heating
element that enables tactile feedback through individually addressable taxels;
2) predefined tactile areas of engraved ITO, that can be layered and combined;
3) complex arrangements of resistance wire that create thin tactile edges. We
present a tablet with 6x4 tactile areas, enabling a tactile numpad, slider, and
thumbstick. We show that the gel is up to 25 times stiffer when activated and
that users detect tactile features reliably (94.8%).
Impacto: Simulating Physical Impact by Combining Tactile Stimulation with
Electrical Muscle Stimulation
Session 1A: Tactile Feedback
/
Lopes, Pedro
/
Ion, Alexandra
/
Baudisch, Patrick
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.11-19
© Copyright 2015 ACM
Summary: We present impacto, a device designed to render the haptic sensation of
hitting or being hit in virtual reality. The key idea that allows the small and
light impacto device to simulate a strong hit is that it decomposes the
stimulus: it renders the tactile aspect of being hit by tapping the skin using
a solenoid; it adds impact to the hit by thrusting the user's arm backwards
using electrical muscle stimulation. The device is self-contained, wireless,
and small enough for wearable use, thus leaves the user unencumbered and able
to walk around freely in a virtual environment. The device is of generic shape,
allowing it to also be worn on legs, so as to enhance the experience of
kicking, or merged into props, such as a baseball bat. We demonstrate how to
assemble multiple impacto units into a simple haptic suit. Participants of our
study rated impact simulated using impacto's combination of solenoid hit and
electrical muscle stimulation as more realistic than either technique in
isolation.
Tactile Animation by Direct Manipulation of Grid Displays
Session 1A: Tactile Feedback
/
Schneider, Oliver S.
/
Israr, Ali
/
MacLean, Karon E.
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.21-30
© Copyright 2015 ACM
Summary: Chairs, wearables, and handhelds have become popular sites for spatial
tactile display. Visual animators, already expert in using time and space to
portray motion, could readily transfer their skills to produce rich haptic
sensations if given the right tools. We introduce the tactile animation object,
a directly manipulated phantom tactile sensation. This abstraction has two key
benefits: 1) efficient, creative, iterative control of spatiotemporal
sensations, and 2) the potential to support a variety of tactile grids,
including sparse displays. We present Mango, an editing tool for animators,
including its rendering pipeline and perceptually-optimized interpolation
algorithm for sparse vibrotactile grids. In our evaluation, professional
animators found it easy to create a variety of vibrotactile patterns, with both
experts and novices preferring the tactile animation object over controlling
actuators individually.
Improving Haptic Feedback on Wearable Devices through Accelerometer
Measurements
Session 1A: Tactile Feedback
/
Blum, Jeffrey R.
/
Frissen, Ilja
/
Cooperstock, Jeremy R.
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.31-36
© Copyright 2015 ACM
Summary: Many variables have been shown to impact whether a vibration stimulus will
be perceived. We present a user study that takes into account not only
previously investigated predictors such as vibration intensity and duration
along with the age of the person receiving the stimulus, but also the amount of
motion, as measured by an accelerometer, at the site of vibration immediately
preceding the stimulus. This is a more specific measure than in previous
studies showing an effect on perception due to gross conditions such as
walking. We show that a logistic regression model including prior acceleration
is significantly better at predicting vibration perception than a model
including only vibration intensity, duration and participant age. In addition
to the overall regression, we discuss individual participant differences and
measures of classification performance for real-world applications. Our
expectation is that haptic interface designers will be able to use such results
to design better vibrations that are perceivable under the user's current
activity conditions, without being annoyingly loud or jarring, eventually
approaching "perceptually equivalent" feedback independent of motion.
cLuster: Smart Clustering of Free-Hand Sketches on Large Interactive
Surfaces
Session 1B: Large Displays, Large Movements
/
Perteneder, Florian
/
Bresler, Martin
/
Grossauer, Eva-Maria
/
Leong, Joanne
/
Haller, Michael
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.37-46
© Copyright 2015 ACM
Summary: Structuring and rearranging free-hand sketches on large interactive surfaces
typically requires making multiple stroke selections. This can be both
time-consuming and fatiguing in the absence of well-designed selection tools.
Investigating the concept of automated clustering, we conducted a background
study which highlighted the fact that people have varying perspectives on how
elements in sketches can and should be grouped. In response to these diverse
user expectations, we present cLuster, a flexible, domain-independent
clustering approach for free-hand sketches. Our approach is designed to accept
an initial user selection, which is then used to calculate a linear combination
of pre-trained perspectives in real-time. The remaining elements are then
clustered. An initial evaluation revealed that in many cases, only a few
corrections were necessary to achieve the desired clustering results. Finally,
we demonstrate the utility of our approach in a variety of application
scenarios.
GravitySpot: Guiding Users in Front of Public Displays Using On-Screen
Visual Cues
Session 1B: Large Displays, Large Movements
/
Alt, Florian
/
Bulling, Andreas
/
Gravanis, Gino
/
Buschek, Daniel
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.47-56
© Copyright 2015 ACM
Summary: Users tend to position themselves in front of interactive public displays in
such a way as to best perceive its content. Currently, this sweet spot is
implicitly defined by display properties, content, the input modality, as well
as space constraints in front of the display. We present GravitySpot -- an
approach that makes sweet spots flexible by actively guiding users to arbitrary
target positions in front of displays using visual cues. Such guidance is
beneficial, for example, if a particular input technology only works at a
specific distance or if users should be guided towards a non-crowded area of a
large display. In two controlled lab studies (n=29) we evaluate different
visual cues based on color, shape, and motion, as well as position-to-cue
mapping functions. We show that both the visual cues and mapping functions
allow for fine-grained control over positioning speed and accuracy. Findings
are complemented by observations from a 3-month real-world deployment.
Tiltcasting: 3D Interaction on Large Displays using a Mobile Device
Session 1B: Large Displays, Large Movements
/
Pietroszek, Krzysztof
/
Wallace, James R.
/
Lank, Edward
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.57-62
© Copyright 2015 ACM
Summary: We develop and formally evaluate a metaphor for smartphone interaction with
3D environments: Tiltcasting. Under the Tiltcasting metaphor, users interact
within a rotatable 2D plane that is "cast" from their phone's interactive
display into 3D space. Through an empirical validation, we show that
Tiltcasting supports efficient pointing, interaction with occluded objects,
disambiguation between nearby objects, and object selection and manipulation in
fully addressable 3D space. Our technique out-performs existing target agnostic
pointing implementations, and approaches the performance of physical pointing
with an off-the-shelf smartphone.
Gunslinger: Subtle Arms-down Mid-air Interaction
Session 1B: Large Displays, Large Movements
/
Liu, Mingyu
/
Nancel, Mathieu
/
Vogel, Daniel
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.63-71
© Copyright 2015 ACM
Summary: We describe Gunslinger, a mid-air interaction technique using barehand
postures and gestures. Unlike past work, we explore a relaxed arms-down
position with both hands interacting at the sides of the body. It features
"hand-cursor" feedback to communicate recognized hand posture, command mode and
tracking quality; and a simple, but flexible hand posture recognizer. Although
Gunslinger is suitable for many usage contexts, we focus on integrating mid-air
gestures with large display touch input. We show how the Gunslinger form factor
enables an interaction language that is equivalent, coherent, and compatible
with large display touch input. A four-part study evaluates Midas Touch,
posture recognition feedback, pointing and clicking, and general usability.
Encore: 3D Printed Augmentation of Everyday Objects with Printed-Over,
Affixed and Interlocked Attachments
Session 2A: Fabrication 1 -- Augmentation
/
Chen, Xiang 'Anthony'
/
Coros, Stelian
/
Mankoff, Jennifer
/
Hudson, Scott E.
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.73-82
© Copyright 2015 ACM
Summary: One powerful aspect of 3D printing is its ability to extend, repair, or more
generally modify everyday objects. However, nearly all existing work implicitly
assumes that whole objects are to be printed from scratch. Designing objects as
extensions or enhancements of existing ones is a laborious process in most of
today's 3D authoring tools. This paper presents a framework for 3D printing to
augment existing objects that covers a wide range of attachment options. We
illustrate the framework through three exemplar attachment techniques --
print-over, print-to-affix and print-through, implemented in Encore, a design
tool that supports a set of analysis metrics relating to viability, durability
and usability that are visualized for the user to explore design options and
tradeoffs. Encore also generates 3D models for production, addressing issues
such as support jigs and contact geometry between the attached part and the
original object. Our validation helps to illustrate the strengths and
weaknesses of each technique. For example, print-over is stronger than
print-to-affix with adhesives, and all the techniques' strengths are affected
by surface curvature.
Patching Physical Objects
Session 2A: Fabrication 1 -- Augmentation
/
Teibrich, Alexander
/
Mueller, Stefanie
/
Guimbretière, François
/
Kovacs, Robert
/
Neubert, Stefan
/
Baudisch, Patrick
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.83-91
© Copyright 2015 ACM
Summary: Personal fabrication is currently a one-way process: Once an object has been
fabricated with a 3D printer, it cannot be changed anymore; any change requires
printing a new version from scratch. The problem is that this approach ignores
the nature of design iteration, i.e. that in subsequent iterations large parts
of an object stay the same and only small parts change. This makes fabricating
from scratch feel unnecessary and wasteful.
In this paper, we propose a different approach: instead of re-printing the
entire object from scratch, we suggest patching the existing object to reflect
the next design iteration. We built a system on top of a 3D printer that
accomplishes this: Users mount the existing object into the 3D printer, then
load both the original and the modified 3D model into our software, which in
turn calculates how to patch the object. After identifying which parts to
remove and what to add, our system locates the existing object in the printer
using the system's built-in 3D scanner. After calibrating the orientation, a
mill first removes the outdated geometry, then a print head prints the new
geometry in place.
Since only a fraction of the entire object is refabricated, our approach
reduces material consumption and plastic waste (for our example objects by 82%
and 93% respectively).
ReForm: Integrating Physical and Digital Design through Bidirectional
Fabrication
Session 2A: Fabrication 1 -- Augmentation
/
Weichel, Christian
/
Hardy, John
/
Alexander, Jason
/
Gellersen, Hans
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.93-102
© Copyright 2015 ACM
Summary: Digital fabrication machines such as 3D printers and laser-cutters allow
users to produce physical objects based on virtual models. The creation process
is currently unidirectional: once an object is fabricated it is separated from
its originating virtual model. Consequently, users are tied into digital
modeling tools, the virtual design must be completed before fabrication, and
once fabricated, re-shaping the physical object no longer influences the
digital model. To provide a more flexible design process that allows objects to
iteratively evolve through both digital and physical input, we introduce
bidirectional fabrication. To demonstrate the concept, we built ReForm, a
system that integrates digital modeling with shape input, shape output,
annotation for machine commands, and visual output. By continually
synchronizing the physical object and digital model it supports object
versioning to allow physical changes to be undone. Through application
examples, we demonstrate the benefits of ReForm to the digital fabrication
process.
Makers' Marks: Physical Markup for Designing and Fabricating Functional
Objects
Session 2A: Fabrication 1 -- Augmentation
/
Savage, Valkyrie
/
Follmer, Sean
/
Li, Jingyi
/
Hartmann, Björn
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.103-108
© Copyright 2015 ACM
Summary: To fabricate functional objects, designers create assemblies combining
existing parts (e.g., mechanical hinges, electronic components) with
custom-designed geometry (e.g., enclosures). Modeling complex assemblies is
outside the reach of the growing number of novice "makers" with access to
digital fabrication tools. We aim to allow makers to design and 3D print
functional mechanical and electronic assemblies. Based on a formative
exploration, we created Makers' Marks, a system based on physically authoring
assemblies with sculpting materials and annotation stickers. Makers physically
sculpt the shape of an object and attach stickers to place existing parts or
high-level features (such as parting lines). Our tool extracts the 3D pose of
these annotations from a scan of the design, then synthesizes the geometry
needed to support integrating desired parts using a library of clearance and
mounting constraints. The resulting designs can then be easily 3D printed and
assembled. Our approach enables easy creation of complex objects such as TUIs,
and leverages physical materials for tangible manipulation and understanding
scale. We validate our tool through several design examples: a custom game
controller, an animated toy figure, a friendly baby monitor, and a hinged box
with integrated alarm.
Procedural Modeling Using Autoencoder Networks
Session 2B: 3D & Augmented Reality
/
Yumer, Mehmet Ersin
/
Asente, Paul
/
Mech, Radomir
/
Kara, Levent Burak
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.109-118
© Copyright 2015 ACM
Summary: Procedural modeling systems allow users to create high quality content
through parametric, conditional or stochastic rule sets. While such approaches
create an abstraction layer by freeing the user from direct geometry editing,
the nonlinear nature and the high number of parameters associated with such
design spaces result in arduous modeling experiences for non-expert users. We
propose a method to enable intuitive exploration of such high dimensional
procedural modeling spaces within a lower dimensional space learned through
autoencoder network training. Our method automatically generates a
representative training dataset from the procedural modeling rule set based on
shape similarity features. We then leverage the samples in this dataset to
train an autoencoder neural network, while also structuring the learned lower
dimensional space for continuous exploration with respect to shape features. We
demonstrate the efficacy our method with user studies where designers create
content with more than 10-fold faster speeds using our system compared to the
classic procedural modeling interface.
SHOCam: A 3D Orbiting Algorithm
Session 2B: 3D & Augmented Reality
/
Ortega, Michael
/
Stuerzlinger, Wolfgang
/
Scheurich, Doug
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.119-128
© Copyright 2015 ACM
Summary: In this paper we describe a new orbiting algorithm, called SHOCam, which
enables simple, safe and visually attractive control of a camera moving around
3D objects. Compared with existing methods, SHOCam provides a more consistent
mapping between the user's interaction and the path of the camera by
substantially reducing variability in both camera motion and look direction.
Also, we present a new orbiting method that prevents the camera from
penetrating object(s), making the visual feedback -- and with it the user
experience -- more pleasing and also less error prone. Finally, we present new
solutions for orbiting around multiple objects and multi-scale environments.
FoveAR: Combining an Optically See-Through Near-Eye Display with
Projector-Based Spatial Augmented Reality
Session 2B: 3D & Augmented Reality
/
Benko, Hrvoje
/
Ofek, Eyal
/
Zheng, Feng
/
Wilson, Andrew D.
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.129-135
© Copyright 2015 ACM
Summary: Optically see-through (OST) augmented reality glasses can overlay
spatially-registered computer-generated content onto the real world. However,
current optical designs and weight considerations limit their diagonal field of
view to less than 40 degrees, making it difficult to create a sense of
immersion or give the viewer an overview of the augmented reality space. We
combine OST glasses with a projection-based spatial augmented reality display
to achieve a novel display hybrid, called FoveAR, capable of greater than 100
degrees field of view, view dependent graphics, extended brightness and color,
as well as interesting combinations of public and personal data display. We
contribute details of our prototype implementation and an analysis of the
interactive design space that our system enables. We also contribute four
prototype experiences showcasing the capabilities of FoveAR as well as
preliminary user feedback providing insights for enhancing future FoveAR
experiences.
Projectibles: Optimizing Surface Color For Projection
Session 2B: 3D & Augmented Reality
/
Jones, Brett R.
/
Sodhi, Rajinder
/
Budhiraja, Pulkit
/
Karsch, Kevin
/
Bailey, Brian
/
Forsyth, David
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.137-146
© Copyright 2015 ACM
Summary: Typically video projectors display images onto white screens, which can
result in a washed out image. Projectibles algorithmically control the display
surface color to increase the contrast and resolution. By combining a printed
image with projected light, we can create animated, high resolution, high
dynamic range visual experiences for video sequences. We present two algorithms
for separating an input video sequence into a printed component and projected
component, maximizing the combined contrast and resolution while minimizing any
visual artifacts introduced from the decomposition. We present empirical
measurements of real-world results of six example video sequences, subjective
viewer feedback ratings, and we discuss the benefits and limitations of
Projectibles. This is the first approach to combine a static display with a
dynamic display for the display of video, and the first to optimize surface
color for projection of video.
Tracko: Ad-hoc Mobile 3D Tracking Using Bluetooth Low Energy and Inaudible
Signals for Cross-Device Interaction
Session 3A: Sensing Techniques
/
Jin, Haojian
/
Holz, Christian
/
Hornbæk, Kasper
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.147-156
© Copyright 2015 ACM
Summary: While current mobile devices detect the presence of surrounding devices,
they lack a truly spatial awareness to bring them into the user's natural 3D
space. We present Tracko, a 3D tracking system between two or more commodity
devices without added components or device synchronization. Tracko achieves
this by fusing three signal types. 1) Tracko infers the presence of and rough
distance to other devices from the strength of Bluetooth low energy signals. 2)
Tracko exchanges a series of inaudible stereo sounds and derives a set of
accurate distances between devices from the difference in their arrival times.
A Kalman filter integrates both signal cues to place collocated devices in a
shared 3D space, combining the robustness of Bluetooth with the accuracy of
audio signals for relative 3D tracking. 3) Tracko incorporates inertial sensors
to refine 3D estimates and support quick interactions. Tracko robustly tracks
devices in 3D with a mean error of 6.5 cm within 0.5 m and a 15.3 cm error
within 1 m, which validates Trackoffs suitability for cross-device
interactions.
EM-Sense: Touch Recognition of Uninstrumented, Electrical and
Electromechanical Objects
Session 3A: Sensing Techniques
/
Laput, Gierad
/
Yang, Chouchang
/
Xiao, Robert
/
Sample, Alanson
/
Harrison, Chris
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.157-166
© Copyright 2015 ACM
Summary: Most everyday electrical and electromechanical objects emit small amounts of
electromagnetic (EM) noise during regular operation. When a user makes physical
contact with such an object, this EM signal propagates through the user, owing
to the conductivity of the human body. By modifying a small, low-cost,
software-defined radio, we can detect and classify these signals in real-time,
enabling robust on-touch object detection. Unlike prior work, our approach
requires no instrumentation of objects or the environment; our sensor is
self-contained and can be worn unobtrusively on the body. We call our technique
EM-Sense and built a proof-of-concept smartwatch implementation. Our studies
show that discrimination between dozens of objects is feasible, independent of
wearer, time and local environment.
Tomo: Wearable, Low-Cost Electrical Impedance Tomography for Hand Gesture
Recognition
Session 3A: Sensing Techniques
/
Zhang, Yang
/
Harrison, Chris
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.167-173
© Copyright 2015 ACM
Summary: We present Tomo, a wearable, low-cost system using Electrical Impedance
Tomography (EIT) to recover the interior impedance geometry of a user's arm.
This is achieved by measuring the cross-sectional impedances between all pairs
of eight electrodes resting on a user's skin. Our approach is sufficiently
compact and low-powered that we integrated the technology into a prototype
wrist- and armband, which can monitor and classify gestures in real-time. We
conducted a user study that evaluated two gesture sets, one focused on gross
hand gestures and another using thumb-to-finger pinches. Our wrist location
achieved 97% and 87% accuracies on these gesture sets respectively, while our
arm location achieved 93% and 81%. We ultimately envision this technique being
integrated into future smartwatches, allowing hand gestures and direct touch
manipulation to work synergistically to support interactive tasks on small
screens.
Corona: Positioning Adjacent Device with Asymmetric Bluetooth Low Energy
RSSI Distributions
Session 3A: Sensing Techniques
/
Jin, Haojian
/
Xu, Cheng
/
Lyons, Kent
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.175-179
© Copyright 2015 ACM
Summary: We introduce Corona, a novel spatial sensing technique that implicitly
locates adjacent mobile devices in the same plane by examining asymmetric
Bluetooth Low Energy RSSI distributions. The underlying phenomenon is that the
off-center BLE antenna and asymmetric radio frequency topology create a
characteristic Bluetooth RSSI distribution around the device. By comparing the
real-time RSSI readings against a RSSI distribution model, each device can
derive the relative position of the other adjacent device. Our experiments
using an iPhone and iPad Mini show that Corona yields position estimation at
50% accuracy within a 2cm range, or 85% for the best two candidates. We
developed an application to combine Corona with accelerometer readings to
mitigate ambiguity and enable cross-device interactions on adjacent devices.
SceneSkim: Searching and Browsing Movies Using Synchronized Captions,
Scripts and Plot Summaries
Session 3B: Intelligent Information Interfaces
/
Pavel, Amy
/
Goldman, Dan B.
/
Hartmann, Björn
/
Agrawala, Maneesh
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.181-190
© Copyright 2015 ACM
Summary: Searching for scenes in movies is a time-consuming but crucial task for film
studies scholars, film professionals, and new media artists. In pilot
interviews we have found that such users search for a wide variety of clips --
e.g., actions, props, dialogue phrases, character performances, locations --
and they return to particular scenes they have seen in the past. Today, these
users find relevant clips by watching the entire movie, scrubbing the video
timeline, or navigating via DVD chapter menus. Increasingly, users can also
index films through transcripts -- however, dialogue often lacks visual
context, character names, and high level event descriptions. We introduce
SceneSkim, a tool for searching and browsing movies using synchronized
captions, scripts and plot summaries. Our interface integrates information from
such sources to allow expressive search at several levels of granularity:
Captions provide access to accurate dialogue, scripts describe shot-by-shot
actions and settings, and plot summaries contain high-level event descriptions.
We propose new algorithms for finding word-level caption to script alignments,
parsing text scripts, and aligning plot summaries to scripts. Film studies
graduate students evaluating SceneSkim expressed enthusiasm about the usability
of the proposed system for their research and teaching.
Capture-Time Feedback for Recording Scripted Narration
Session 3B: Intelligent Information Interfaces
/
Rubin, Steve
/
Berthouzoz, Floraine
/
Mysore, Gautham J.
/
Agrawala, Maneesh
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.191-199
© Copyright 2015 ACM
Summary: Well-performed audio narrations are a hallmark of captivating podcasts,
explainer videos, radio stories, and movie trailers. To record these
narrations, professional voiceover actors follow guidelines that describe how
to use low-level vocal components -- volume, pitch, timbre, and tempo -- to
deliver performances that emphasize important words while maintaining variety,
flow and diction. Yet, these techniques are not well-known outside the
professional voiceover community, especially among hobbyist producers looking
to create their own narrations. We present Narration Coach, an interface that
assists novice users in recording scripted narrations. As a user records her
narration, our system synchronizes the takes to her script, provides text
feedback about how well she is meeting the expert voiceover guidelines, and
resynthesizes her recordings to help her hear how she can speak better.
Improving Automated Email Tagging with Implicit Feedback
Session 3B: Intelligent Information Interfaces
/
Sorower, Mohammad S.
/
Slater, Michael
/
Dietterich, Thomas G.
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.201-211
© Copyright 2015 ACM
Summary: Tagging email is an important tactic for managing information overload.
Machine learning methods can help the user with this task by predicting tags
for incoming email messages. The natural user interface displays the predicted
tags on the email message, and the user doesn't need to do anything unless
those predictions are wrong (in which case, the user can delete the incorrect
tags and add the missing tags). From a machine learning perspective, this means
that the learning algorithm never receives confirmation that its predictions
are correct -- it only receives feedback when it makes a mistake. This can lead
to slower learning, particularly when the predictions were not very confident,
and hence, the learning algorithm would benefit from positive feedback. One
could assume that if the user never changes any tag, then the predictions are
correct, but users sometimes forget to correct the tags, presumably because
they are focused on the content of the email messages and fail to notice
incorrect and missing tags. The aim of this paper is to determine whether
implicit feedback can provide useful additional training examples to the email
prediction subsystem of TaskTracer, known as EP2 (Email Predictor 2). Our
hypothesis is that the more time a user spends working on an email message, the
more likely it is that the user will notice tag errors and correct them. If no
corrections are made, then perhaps it is safe for the learning system to treat
the predicted tags as being correct and train accordingly. This paper proposes
three algorithms (and two baselines) for incorporating implicit feedback into
the EP2 tag predictor. These algorithms are then evaluated using email
interaction and tag correction events collected from 14 user-study participants
as they performed email-directed tasks while using TaskTracer EP2. The results
show that implicit feedback produces important increases in training feedback,
and hence, significant reductions in subsequent prediction errors despite the
fact that the implicit feedback is not perfect. We conclude that implicit
feedback mechanisms can provide a useful performance boost for email tagging
systems.
Codo: Fundraising with Conditional Donations
Session 3B: Intelligent Information Interfaces
/
Beltran, Juan Felipe
/
Siddique, Aysha
/
Abouzied, Azza
/
Chen, Jay
Proceedings of the 2015 ACM Symposium on User Interface Software and
Technology
2015-11-05
v.1
p.213-222
© Copyright 2015 ACM
Summary: Crowdfunding websites like Kickstarter and Indiegogo offer project
organizers the ability to market, fund, and build a community around their
campaign. While offering support and flexibility for organizers, crowdfunding
sites provide very little control to donors. In this paper, we investigate the
idea of empowering donors by allowing them to specify conditions for their
crowdfunding contributions. We introduce a crowdfunding system, Codo, that
allows donors to specify conditional donations. Codo allow donors to contribute
to a campaign but hold off on their contribution until certain specific
conditions are met (e.g. specific members or groups contribute a certain
amount). We begin with a micro study to assess several specific conditional
donations based on their comprehensibility and usage likelihood. Based on this
study, we formalize conditional donations into a general grammar that captures
a broad set of useful conditions. We demonstrate the feasibility of resolving
conditions in our grammar by elegantly transforming conditional donations into
a system of linear inequalities that are efficiently resolved using
off-the-shelf linear program solvers. Finally, we designed a user-friendly
crowdfunding interface that supports conditional donations for an actual fund
raising campaign and assess the potential of conditional donations through this
campaign. We find preliminary evidence that roughly 1 in 3 donors make
conditional donations and that conditional donors donate more compared to
direct donors.
