SlideShare a Scribd company logo
Bigness Info. in Data Image Summarization Video Summarization End
Image and Video Summarization
Jeffrey A. Bilmes
Professor
Departments of Electrical Engineering
& Computer Science and Engineering
University of Washington, Seattle
http://melodi.ee.washington.edu/~bilmes
and
Visiting Scientist, Google Research
Wednesday, Dec 7th, 2016
J. Bilmes Image and Video Summarization — 12/7/2016 page 1 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Outline
1 Bigness
2 Information In Data
3 Image Summarization
4 Video Summarization
5 End
J. Bilmes Image and Video Summarization — 12/7/2016 page 2 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Summarization
What is summarization?
Why do we need summarization?
J. Bilmes Image and Video Summarization — 12/7/2016 page 4 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Bigness
J. Bilmes Image and Video Summarization — 12/7/2016 page 5 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Water
H2O molecules
small (n-body)
medium (fluid dynamics, viscosity, compressibility),
large (global weather systems, meteorology).
Same underlying molecular collision events!
J. Bilmes Image and Video Summarization — 12/7/2016 page 6 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Neurons
Neurons
small (neural spike trains, population coding)
medium (intelligence, consciousness, psychology)
large (society, social choice, wisdom of the crowd)
Same underlying electrical and chemical impulses.
J. Bilmes Image and Video Summarization — 12/7/2016 page 7 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Bigger is Different
“More is Different”, P.W. Anderson, 1972
(Nobel laureate). “The ability to reduce
everything to simple fundamental laws does
not imply the ability to start from those laws
and reconstruct the universe.”
“. . . alterations of being . . . are not only the
transition of one magnitude into another,
but a transition from quantity into quality,”
Hegel, The Science of Logic, 1816
J. Bilmes Image and Video Summarization — 12/7/2016 page 8 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Big Data is Different Data
Hypothesis: extremely large data sets offer qualitatively different
capabilities than small data sets.
Evidence: Image Completion (Hays & Efros, 2007)
“our initial experiments . . . on a dataset of ten thousand images
were very discouraging. However, increasing the image collection
to two million yielded a qualitative leap in performance”
J. Bilmes Image and Video Summarization — 12/7/2016 page 9 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Modern Times
Big Data is Big and Getting Even Bigger.
Sensors &
Devices
Social Media
VoIP
Enterprise
Data
Now A Few Years
From Now
A Few Years
Ago
VolumeofData
2.5 quintillion bytes (2.5 million terabytes) of data/day (IBM)
>90% of the world’s data has been created in the last two years.
J. Bilmes Image and Video Summarization — 12/7/2016 page 10 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Big Data in Machine Learning
Statistics, Machine Learning, and Artificial Intelligence (AI)
“There’s no data like more data”,
Computational Consequences:
Massive computational resource demands!
Research opportunities to address new computational challenges
1 systems programming, parallel and distributed computing,
network topologies, efficient databases, GPUs.
2 Examples: map reduce, Hadoop, GraphLab, HaLoop, Greenplum,
Asterix, Spark, SystemML, MLBase, Myria, etc.
J. Bilmes Image and Video Summarization — 12/7/2016 page 11 / 35
Bigness Info. in Data Image Summarization Video Summarization End
The Two Foundations of Big Data?
Data
StatisticalSignificance
ParallelComputingSystems
??????????????
Large Data
StatisticalSignificance
Larg
J. Bilmes Image and Video Summarization — 12/7/2016 page 12 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Goal: Data to Information
Data is:
Streaming
Torrential
Relentless
Multi-modal
Mostly Unstructured
Sensors/Actuators
Redundant
High Dimensional
Distributed
J. Bilmes Image and Video Summarization — 12/7/2016 page 13 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Big Data is Different Data: A Proposition
Hypothesis: extremely large data sets offer
qualitatively different capabilities than small
data sets.
Problem: Big data sets are big, unwieldy,
computationally challenging, and often highly
redundant.
Research Quest: Can statistical predictions and
actions be made cost effectively using the right
data management strategies?
Yes, by reducing redundancy.
J. Bilmes Image and Video Summarization — 12/7/2016 page 14 / 35
Bigness Info. in Data Image Summarization Video Summarization End
How to identify and measure redundancy?
J. Bilmes Image and Video Summarization — 12/7/2016 page 15 / 35
Bigness Info. in Data Image Summarization Video Summarization End
How to identify and measure redundancy?
J. Bilmes Image and Video Summarization — 12/7/2016 page 16 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Measuring Information in Data
What is information?
Information Theory (entropy, mutual information) ⇔ probability
distributions.
Kolmogorov Complexity ⇔ algorithms & models of computation.
Information measures over non-random data samples (e.g., images).
f( ) = f( , )
< f( , ) < f( , )
J. Bilmes Image and Video Summarization — 12/7/2016 page 18 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Measuring Information in Data
Diminishing returns:
The more you have, the less valuable is anything you don’t have.
f( )f( )-
f( )
- f( )
≥
J. Bilmes Image and Video Summarization — 12/7/2016 page 19 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Example: Number of Colors of Balls in Urns
Consider an urn containing colored balls. Given a set S of balls,
f (S) counts the number of distinct colors.
Initial value: 2 (colors in urn).
New value with added blue ball: 3
Initial value: 3 (colors in urn).
New value with added blue ball: 3
Submodularity : Incremental Value of Object Diminishes in a
Larger Context (diminishing returns). Thus, f is submodular.
J. Bilmes Image and Video Summarization — 12/7/2016 page 20 / 35
Bigness Info. in Data Image Summarization Video Summarization End
As the data set size grow . . .
There is no data like more data ⇒ more data is like no more data.
From Andrew Ng’s Stanford
machine learning class, 2011
J. Bilmes Image and Video Summarization — 12/7/2016 page 21 / 35
Bigness Info. in Data Image Summarization Video Summarization End
As the data set sizes grow . . .
0.70
0.75
0.80
0.85
0.90
0.95
1.00
0.1 1 10 100 1000
Millions of Words
TestAccuracy
Memory-Based
Winnow
Perceptron
Naïve Bayes
Banko & Brill 2001
(Riccardi & Hakkani-Tür, 2005, Speech Recognition) (Callison-Burch&Bloodgood, 2010, Machine Translation)
Tong & Koller, 2001 (Soon, Ng, Lim, 2001, Coreference Resolution)
50 100 150 200 250
Number of Training Examples
0
0.2
0.4
0.6
0.8
1
Accuracy
(Kadie, 1995, Generic Classification)
Sentiment Tutorial, Chris Potts, Stanford Ling., 2011
78
80
82
84
86
88
90
92
700 1.750 3.500 7.000 10.500 14.000 17.500 21.000
Overallaccuracy(%)
Training set size
SVMs
DTs
( Kavzoglu & Colkesen, 2012, Image Classification)
Speed, memory, attention, problem solving
playing game Luminosity
http://www.lumosity.com/blog/how-much-and-how-often-should-i-train/
J. Bilmes Image and Video Summarization — 12/7/2016 page 22 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Submodularity and Learning Curves
Proposition
Let V = {1, 2, . . . , n} be a finite ground set, and let f : 2V
→ R be a
set function. If for all permutations σ of V , we have that for all i ≤ j:
f (σj |Si−1) ≥ f (σj |Sj−1) (1)
with Si = {σ1, σ2, . . . , σi }, then f is submodular.
Learning curves might not be exactly submodular, but
submodularity seems a reasonable model.
J. Bilmes Image and Video Summarization — 12/7/2016 page 23 / 35
Bigness Info. in Data Image Summarization Video Summarization End
What is Summarization?
1 Start with a massive data set (images, videos, etc.), set V .
2 Identify a good (submodular) information function f (by hand or
by machine learning) that represents information in V .
3 Find a subset A ⊆ V of a given size that retains as much
information as possible.
4 Luckily, this normally exponential time problem can be done
computationally efficiently!!
J. Bilmes Image and Video Summarization — 12/7/2016 page 24 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Modern Image Collections
Many images, also that have a higher level gestalt than just a few.
J. Bilmes Image and Video Summarization — 12/7/2016 page 26 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Image Summarization
Task: Summarize collection
of images by representative
subset of the images
Applications:
Summarizing your
holiday pictures.
Summarizing image
search results
Efficient browsing of
image collections
Video frame
summarization
Difficulties:
No high level
⇓
J. Bilmes Image and Video Summarization — 12/7/2016 page 27 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Image Summarization - Data Collection
Data Statistics
14 image collections with 100 pictures each
∼ 400 human summaries for every image collection, via Amazon
Turk, about 5500 summaries total!
Example collections:
J. Bilmes Image and Video Summarization — 12/7/2016 page 28 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Image Summarization
Whole collection: 3 best summaries:
3 medium summaries:
3 worst summaries:
J. Bilmes Image and Video Summarization — 12/7/2016 page 29 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Image Summarization
Typical Results - Learnt mixture using Max-Margin
f(∅) = 0 f(V ) = 1
Greedy Min
Average Pruned Random
Max of Learned Mixture
Average Pruned Human
Greedy Max
Average Pruned Random
Average Pruned Human
J. Bilmes Image and Video Summarization — 12/7/2016 page 30 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Real-Time Running Online Video Summarization
Live Video
Feed
Most recent
representative video
snippet (repeating)
Next most recent
representative video
snippet (repeating)
Third most recent
representative video
snippet (repeating)
Fourth most recent
representative video
snippet (repeating)
Least recent
representative video
snippet (repeating)
...
J. Bilmes Image and Video Summarization — 12/7/2016 page 32 / 35
Bigness Info. in Data Image Summarization Video Summarization End
Real-Time Running Online Video Summarization
J. Bilmes Image and Video Summarization — 12/7/2016 page 33 / 35
Bigness Info. in Data Image Summarization Video Summarization End
The End
The End: Thank you!
++
+ +
f(A) f(B) f(A ∪ B)
= f(Ar ) +f(C) + f(Br )
≥
≥
= f(A ∩ B)
f(A ∩ B)
= f(Ar ) + 2f(C) + f(Br )
J. Bilmes Image and Video Summarization — 12/7/2016 page 35 / 35

More Related Content

What's hot

MPEG Compression Standards
MPEG Compression StandardsMPEG Compression Standards
MPEG Compression Standards
Ajay
 
Video Classification Basic
Video Classification Basic Video Classification Basic
Video Classification Basic
Silversparro Technologies
 
ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...
ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...
ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...
Mathias Wien
 
VVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin BrossVVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin Bross
Mathias Wien
 
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
Edge AI and Vision Alliance
 
An Overview of High Efficiency Video Codec HEVC (H.265)
An Overview of High Efficiency Video Codec HEVC (H.265)An Overview of High Efficiency Video Codec HEVC (H.265)
An Overview of High Efficiency Video Codec HEVC (H.265)
Varun Ravi
 
Bandwidth Prediction in Low-Latency Chunked Streaming
Bandwidth Prediction in Low-Latency Chunked StreamingBandwidth Prediction in Low-Latency Chunked Streaming
Bandwidth Prediction in Low-Latency Chunked Streaming
Alpen-Adria-Universität
 
Machine Learning approaches at video compression
Machine Learning approaches at video compression Machine Learning approaches at video compression
Machine Learning approaches at video compression
Roberto Iacoviello
 
AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -
AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -
AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -
Yasuyuki Sugai
 
Understanding MPEG DASH
Understanding MPEG DASHUnderstanding MPEG DASH
Understanding MPEG DASH
Seung-Bum Lee
 
Introduction to H.264 Advanced Video Compression
Introduction to H.264 Advanced Video CompressionIntroduction to H.264 Advanced Video Compression
Introduction to H.264 Advanced Video Compression
Iain Richardson
 
3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...
3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...
3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...
Ryuichi Yasunaga
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human label
Kai-Wen Zhao
 
Presentation - Model Efficiency for Edge AI
Presentation - Model Efficiency for Edge AIPresentation - Model Efficiency for Edge AI
Presentation - Model Efficiency for Edge AI
Qualcomm Research
 
Introduction to HEVC
Introduction to HEVCIntroduction to HEVC
Introduction to HEVC
Yoss Cohen
 
R-CNN
R-CNNR-CNN
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
Nader Karimi
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
Chanuk Lim
 
VVC tutorial at VCIP 2020 together with Benjamin Bross
VVC tutorial at VCIP 2020 together with Benjamin BrossVVC tutorial at VCIP 2020 together with Benjamin Bross
VVC tutorial at VCIP 2020 together with Benjamin Bross
Mathias Wien
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
Ryo Takahashi
 

What's hot (20)

MPEG Compression Standards
MPEG Compression StandardsMPEG Compression Standards
MPEG Compression Standards
 
Video Classification Basic
Video Classification Basic Video Classification Basic
Video Classification Basic
 
ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...
ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...
ICME 2016 - High Efficiency Video Coding - Coding Tools and Specification: HE...
 
VVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin BrossVVC tutorial at ICME 2020 together with Benjamin Bross
VVC tutorial at ICME 2020 together with Benjamin Bross
 
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...“How Transformers are Changing the Direction of Deep Learning Architectures,”...
“How Transformers are Changing the Direction of Deep Learning Architectures,”...
 
An Overview of High Efficiency Video Codec HEVC (H.265)
An Overview of High Efficiency Video Codec HEVC (H.265)An Overview of High Efficiency Video Codec HEVC (H.265)
An Overview of High Efficiency Video Codec HEVC (H.265)
 
Bandwidth Prediction in Low-Latency Chunked Streaming
Bandwidth Prediction in Low-Latency Chunked StreamingBandwidth Prediction in Low-Latency Chunked Streaming
Bandwidth Prediction in Low-Latency Chunked Streaming
 
Machine Learning approaches at video compression
Machine Learning approaches at video compression Machine Learning approaches at video compression
Machine Learning approaches at video compression
 
AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -
AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -
AnsibleではじめるNW設定の自動化について - Cisco(VIRL)編 -
 
Understanding MPEG DASH
Understanding MPEG DASHUnderstanding MPEG DASH
Understanding MPEG DASH
 
Introduction to H.264 Advanced Video Compression
Introduction to H.264 Advanced Video CompressionIntroduction to H.264 Advanced Video Compression
Introduction to H.264 Advanced Video Compression
 
3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...
3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...
3GPP 5G SA Detailed explanation 1(Relationship between 5G Identifier and Virt...
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human label
 
Presentation - Model Efficiency for Edge AI
Presentation - Model Efficiency for Edge AIPresentation - Model Efficiency for Edge AI
Presentation - Model Efficiency for Edge AI
 
Introduction to HEVC
Introduction to HEVCIntroduction to HEVC
Introduction to HEVC
 
R-CNN
R-CNNR-CNN
R-CNN
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
 
VVC tutorial at VCIP 2020 together with Benjamin Bross
VVC tutorial at VCIP 2020 together with Benjamin BrossVVC tutorial at VCIP 2020 together with Benjamin Bross
VVC tutorial at VCIP 2020 together with Benjamin Bross
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
 

Viewers also liked

"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures
"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures
"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures
Edge AI and Vision Alliance
 
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn..."Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
Edge AI and Vision Alliance
 
"Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ...
"Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ..."Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ...
"Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ...
Edge AI and Vision Alliance
 
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ..."New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
Edge AI and Vision Alliance
 
"A Vision of Safety," a Presentation from Nauto
"A Vision of Safety," a Presentation from Nauto"A Vision of Safety," a Presentation from Nauto
"A Vision of Safety," a Presentation from Nauto
Edge AI and Vision Alliance
 
SharePoint 2010 as an effective Learning Gateway
SharePoint 2010 as an effective Learning GatewaySharePoint 2010 as an effective Learning Gateway
SharePoint 2010 as an effective Learning GatewayMike Herrity
 
Sp2 1 public works safety presentation final 6.18.12
Sp2 1  public works safety presentation final 6.18.12Sp2 1  public works safety presentation final 6.18.12
Sp2 1 public works safety presentation final 6.18.12
cityofevanston
 
Applying Media Content Analysis to the Production of Musical Videos as Summar...
Applying Media Content Analysis to the Production of Musical Videos as Summar...Applying Media Content Analysis to the Production of Musical Videos as Summar...
Applying Media Content Analysis to the Production of Musical Videos as Summar...
Chris Huang
 
Howen CCTV System worldwide Application-201309
Howen CCTV System worldwide Application-201309Howen CCTV System worldwide Application-201309
Howen CCTV System worldwide Application-201309Berry Gao
 
Clusterrank
ClusterrankClusterrank
Clusterranknikgarg
 
Content based video summarization into object maps
Content based video summarization into object mapsContent based video summarization into object maps
Content based video summarization into object maps
Universitat Politècnica de Catalunya
 
Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...
Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...
Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...
Shanghai Jiao Tong University(上海交通大学)
 
Perceptual Video Coding
Perceptual Video Coding Perceptual Video Coding
Video summarization using clustering
Video summarization using clusteringVideo summarization using clustering
Video summarization using clustering
Sahil Biswas
 
The Summary Response Assignment
The Summary Response AssignmentThe Summary Response Assignment
The Summary Response Assignment
rlewitzki
 
Introduction to multi gpu deep learning with DIGITS 2 - Mike Wang
Introduction to multi gpu deep learning with DIGITS 2 - Mike WangIntroduction to multi gpu deep learning with DIGITS 2 - Mike Wang
Introduction to multi gpu deep learning with DIGITS 2 - Mike Wang
PAPIs.io
 
VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...
VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...
VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...
Journal For Research
 

Viewers also liked (20)

"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures
"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures
"The Vision AI Start-ups That Matter Most," a Presentation from Cognite Ventures
 
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn..."Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...
 
"Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ...
"Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ..."Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ...
"Imaging + AI: Opportunities Inside the Car and Beyond," a Presentation from ...
 
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ..."New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
 
"A Vision of Safety," a Presentation from Nauto
"A Vision of Safety," a Presentation from Nauto"A Vision of Safety," a Presentation from Nauto
"A Vision of Safety," a Presentation from Nauto
 
SharePoint 2010 as an effective Learning Gateway
SharePoint 2010 as an effective Learning GatewaySharePoint 2010 as an effective Learning Gateway
SharePoint 2010 as an effective Learning Gateway
 
Sp2 1 public works safety presentation final 6.18.12
Sp2 1  public works safety presentation final 6.18.12Sp2 1  public works safety presentation final 6.18.12
Sp2 1 public works safety presentation final 6.18.12
 
Applying Media Content Analysis to the Production of Musical Videos as Summar...
Applying Media Content Analysis to the Production of Musical Videos as Summar...Applying Media Content Analysis to the Production of Musical Videos as Summar...
Applying Media Content Analysis to the Production of Musical Videos as Summar...
 
Howen CCTV System worldwide Application-201309
Howen CCTV System worldwide Application-201309Howen CCTV System worldwide Application-201309
Howen CCTV System worldwide Application-201309
 
Clusterrank
ClusterrankClusterrank
Clusterrank
 
Deposition Summary
Deposition SummaryDeposition Summary
Deposition Summary
 
Content based video summarization into object maps
Content based video summarization into object mapsContent based video summarization into object maps
Content based video summarization into object maps
 
Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...
Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...
Paralleling Variable Block Size Motion Estimation of HEVC On CPU plus GPU Pla...
 
Perceptual Video Coding
Perceptual Video Coding Perceptual Video Coding
Perceptual Video Coding
 
Video summarization using clustering
Video summarization using clusteringVideo summarization using clustering
Video summarization using clustering
 
Deviant Sex PPT
Deviant Sex PPTDeviant Sex PPT
Deviant Sex PPT
 
The Summary Response Assignment
The Summary Response AssignmentThe Summary Response Assignment
The Summary Response Assignment
 
Introduction to multi gpu deep learning with DIGITS 2 - Mike Wang
Introduction to multi gpu deep learning with DIGITS 2 - Mike WangIntroduction to multi gpu deep learning with DIGITS 2 - Mike Wang
Introduction to multi gpu deep learning with DIGITS 2 - Mike Wang
 
VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...
VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...
VIDEO SUMMARIZATION: CORRELATION FOR SUMMARIZATION AND SUBTRACTION FOR RARE E...
 
MaPU-HPCA2016
MaPU-HPCA2016MaPU-HPCA2016
MaPU-HPCA2016
 

Similar to "Image and Video Summarization," a Presentation from the University of Washington

Carlo Colicchio: Big Data for business
Carlo Colicchio: Big Data for businessCarlo Colicchio: Big Data for business
Carlo Colicchio: Big Data for business
Carlo Vaccari
 
Puglia marac-file formats-20111020
Puglia marac-file formats-20111020Puglia marac-file formats-20111020
Puglia marac-file formats-20111020MARAC Bethlehem PC
 
Improving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisationImproving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisation
ThoughtWorks Studios
 
Improving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisationImproving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisation
Thoughtworks
 
C1802031219
C1802031219C1802031219
C1802031219
IOSR Journals
 
LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...
LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...
LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...
IJDKP
 
Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...
Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...
Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...
IJERA Editor
 
SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...
SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...
SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...
BigData_Europe
 
Fare Loyalty con i Big Data: quali sfide?
Fare Loyalty con i Big Data: quali sfide?Fare Loyalty con i Big Data: quali sfide?
Fare Loyalty con i Big Data: quali sfide?
Osservatorio Fedeltà Università di Parma
 
M.tech Third progress Presentation
M.tech Third progress PresentationM.tech Third progress Presentation
M.tech Third progress Presentation
NEERAJ BAGHEL
 
Early Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV AdvertisingEarly Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV Advertising
Jeffrey Storan
 
Early Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV AdvertisingEarly Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV Advertising
Jeff Storan
 
IRJET - Applications of Image and Video Deduplication: A Survey
IRJET -  	  Applications of Image and Video Deduplication: A SurveyIRJET -  	  Applications of Image and Video Deduplication: A Survey
IRJET - Applications of Image and Video Deduplication: A Survey
IRJET Journal
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
IJERD Editor
 
Effective Communication Of Data Inspired by Stephen Few
Effective Communication Of Data Inspired by Stephen FewEffective Communication Of Data Inspired by Stephen Few
Effective Communication Of Data Inspired by Stephen Few
Cory Grenier
 
Enabling a Data Driven Agile Business
Enabling a Data Driven Agile BusinessEnabling a Data Driven Agile Business
Enabling a Data Driven Agile Business
Tharindu Mathew
 
FDS Module I 20.1.2022.ppt
FDS Module I 20.1.2022.pptFDS Module I 20.1.2022.ppt
FDS Module I 20.1.2022.ppt
PerumalPitchandi
 
High Performance BI with Cognos and ParAccel Analytic Database
High Performance BI with Cognos and ParAccel Analytic DatabaseHigh Performance BI with Cognos and ParAccel Analytic Database
High Performance BI with Cognos and ParAccel Analytic Database
Karol Chlasta
 
Using Data Riches A tale of two projects - Ajay Vinze
Using Data Riches A tale of two projects - Ajay VinzeUsing Data Riches A tale of two projects - Ajay Vinze
Using Data Riches A tale of two projects - Ajay Vinze
Institute of Contemporary Sciences
 

Similar to "Image and Video Summarization," a Presentation from the University of Washington (20)

Carlo Colicchio: Big Data for business
Carlo Colicchio: Big Data for businessCarlo Colicchio: Big Data for business
Carlo Colicchio: Big Data for business
 
Puglia marac-file formats-20111020
Puglia marac-file formats-20111020Puglia marac-file formats-20111020
Puglia marac-file formats-20111020
 
Improving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisationImproving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisation
 
Improving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisationImproving business outcomes through rapid data visualisation
Improving business outcomes through rapid data visualisation
 
C1802031219
C1802031219C1802031219
C1802031219
 
LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...
LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...
LOW-COMPLEXITY BIG VIDEO DATA RECORDING ALGORITHMS FOR URBAN SURVEILLANCE SYS...
 
Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...
Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...
Quality Compression for Medical Big Data X-Ray Image using Biorthogonal 5.5 W...
 
SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...
SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...
SC6 Workshop 1: Big Data Europe platform requirements and draft architecture:...
 
Fare Loyalty con i Big Data: quali sfide?
Fare Loyalty con i Big Data: quali sfide?Fare Loyalty con i Big Data: quali sfide?
Fare Loyalty con i Big Data: quali sfide?
 
M.tech Third progress Presentation
M.tech Third progress PresentationM.tech Third progress Presentation
M.tech Third progress Presentation
 
Early Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV AdvertisingEarly Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV Advertising
 
Early Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV AdvertisingEarly Lessons Learned in Applying Big Data To TV Advertising
Early Lessons Learned in Applying Big Data To TV Advertising
 
IRJET - Applications of Image and Video Deduplication: A Survey
IRJET -  	  Applications of Image and Video Deduplication: A SurveyIRJET -  	  Applications of Image and Video Deduplication: A Survey
IRJET - Applications of Image and Video Deduplication: A Survey
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
Effective Communication Of Data Inspired by Stephen Few
Effective Communication Of Data Inspired by Stephen FewEffective Communication Of Data Inspired by Stephen Few
Effective Communication Of Data Inspired by Stephen Few
 
Enabling a Data Driven Agile Business
Enabling a Data Driven Agile BusinessEnabling a Data Driven Agile Business
Enabling a Data Driven Agile Business
 
FDS Module I 20.1.2022.ppt
FDS Module I 20.1.2022.pptFDS Module I 20.1.2022.ppt
FDS Module I 20.1.2022.ppt
 
High Performance BI with Cognos and ParAccel Analytic Database
High Performance BI with Cognos and ParAccel Analytic DatabaseHigh Performance BI with Cognos and ParAccel Analytic Database
High Performance BI with Cognos and ParAccel Analytic Database
 
Using Data Riches A tale of two projects - Ajay Vinze
Using Data Riches A tale of two projects - Ajay VinzeUsing Data Riches A tale of two projects - Ajay Vinze
Using Data Riches A tale of two projects - Ajay Vinze
 
Grc t18
Grc t18Grc t18
Grc t18
 

More from Edge AI and Vision Alliance

"OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a...
"OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a..."OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a...
"OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a...
Edge AI and Vision Alliance
 
“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...
“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...
“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...
Edge AI and Vision Alliance
 
“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...
“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...
“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...
Edge AI and Vision Alliance
 
“What’s Next in On-device Generative AI,” a Presentation from Qualcomm
“What’s Next in On-device Generative AI,” a Presentation from Qualcomm“What’s Next in On-device Generative AI,” a Presentation from Qualcomm
“What’s Next in On-device Generative AI,” a Presentation from Qualcomm
Edge AI and Vision Alliance
 
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
Edge AI and Vision Alliance
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
Edge AI and Vision Alliance
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
Edge AI and Vision Alliance
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
Edge AI and Vision Alliance
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
Edge AI and Vision Alliance
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
Edge AI and Vision Alliance
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
Edge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
Edge AI and Vision Alliance
 

More from Edge AI and Vision Alliance (20)

"OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a...
"OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a..."OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a...
"OpenCV for High-performance, Low-power Vision Applications on Snapdragon," a...
 
“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...
“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...
“Deploying Large Models on the Edge: Success Stories and Challenges,” a Prese...
 
“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...
“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...
“Scaling Vision-based Edge AI Solutions: From Prototype to Global Deployment,...
 
“What’s Next in On-device Generative AI,” a Presentation from Qualcomm
“What’s Next in On-device Generative AI,” a Presentation from Qualcomm“What’s Next in On-device Generative AI,” a Presentation from Qualcomm
“What’s Next in On-device Generative AI,” a Presentation from Qualcomm
 
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 

Recently uploaded

Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
DianaGray10
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 

Recently uploaded (20)

Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 

"Image and Video Summarization," a Presentation from the University of Washington

  • 1. Bigness Info. in Data Image Summarization Video Summarization End Image and Video Summarization Jeffrey A. Bilmes Professor Departments of Electrical Engineering & Computer Science and Engineering University of Washington, Seattle http://melodi.ee.washington.edu/~bilmes and Visiting Scientist, Google Research Wednesday, Dec 7th, 2016 J. Bilmes Image and Video Summarization — 12/7/2016 page 1 / 35
  • 2. Bigness Info. in Data Image Summarization Video Summarization End Outline 1 Bigness 2 Information In Data 3 Image Summarization 4 Video Summarization 5 End J. Bilmes Image and Video Summarization — 12/7/2016 page 2 / 35
  • 3. Bigness Info. in Data Image Summarization Video Summarization End Summarization What is summarization? Why do we need summarization? J. Bilmes Image and Video Summarization — 12/7/2016 page 4 / 35
  • 4. Bigness Info. in Data Image Summarization Video Summarization End Bigness J. Bilmes Image and Video Summarization — 12/7/2016 page 5 / 35
  • 5. Bigness Info. in Data Image Summarization Video Summarization End Water H2O molecules small (n-body) medium (fluid dynamics, viscosity, compressibility), large (global weather systems, meteorology). Same underlying molecular collision events! J. Bilmes Image and Video Summarization — 12/7/2016 page 6 / 35
  • 6. Bigness Info. in Data Image Summarization Video Summarization End Neurons Neurons small (neural spike trains, population coding) medium (intelligence, consciousness, psychology) large (society, social choice, wisdom of the crowd) Same underlying electrical and chemical impulses. J. Bilmes Image and Video Summarization — 12/7/2016 page 7 / 35
  • 7. Bigness Info. in Data Image Summarization Video Summarization End Bigger is Different “More is Different”, P.W. Anderson, 1972 (Nobel laureate). “The ability to reduce everything to simple fundamental laws does not imply the ability to start from those laws and reconstruct the universe.” “. . . alterations of being . . . are not only the transition of one magnitude into another, but a transition from quantity into quality,” Hegel, The Science of Logic, 1816 J. Bilmes Image and Video Summarization — 12/7/2016 page 8 / 35
  • 8. Bigness Info. in Data Image Summarization Video Summarization End Big Data is Different Data Hypothesis: extremely large data sets offer qualitatively different capabilities than small data sets. Evidence: Image Completion (Hays & Efros, 2007) “our initial experiments . . . on a dataset of ten thousand images were very discouraging. However, increasing the image collection to two million yielded a qualitative leap in performance” J. Bilmes Image and Video Summarization — 12/7/2016 page 9 / 35
  • 9. Bigness Info. in Data Image Summarization Video Summarization End Modern Times Big Data is Big and Getting Even Bigger. Sensors & Devices Social Media VoIP Enterprise Data Now A Few Years From Now A Few Years Ago VolumeofData 2.5 quintillion bytes (2.5 million terabytes) of data/day (IBM) >90% of the world’s data has been created in the last two years. J. Bilmes Image and Video Summarization — 12/7/2016 page 10 / 35
  • 10. Bigness Info. in Data Image Summarization Video Summarization End Big Data in Machine Learning Statistics, Machine Learning, and Artificial Intelligence (AI) “There’s no data like more data”, Computational Consequences: Massive computational resource demands! Research opportunities to address new computational challenges 1 systems programming, parallel and distributed computing, network topologies, efficient databases, GPUs. 2 Examples: map reduce, Hadoop, GraphLab, HaLoop, Greenplum, Asterix, Spark, SystemML, MLBase, Myria, etc. J. Bilmes Image and Video Summarization — 12/7/2016 page 11 / 35
  • 11. Bigness Info. in Data Image Summarization Video Summarization End The Two Foundations of Big Data? Data StatisticalSignificance ParallelComputingSystems ?????????????? Large Data StatisticalSignificance Larg J. Bilmes Image and Video Summarization — 12/7/2016 page 12 / 35
  • 12. Bigness Info. in Data Image Summarization Video Summarization End Goal: Data to Information Data is: Streaming Torrential Relentless Multi-modal Mostly Unstructured Sensors/Actuators Redundant High Dimensional Distributed J. Bilmes Image and Video Summarization — 12/7/2016 page 13 / 35
  • 13. Bigness Info. in Data Image Summarization Video Summarization End Big Data is Different Data: A Proposition Hypothesis: extremely large data sets offer qualitatively different capabilities than small data sets. Problem: Big data sets are big, unwieldy, computationally challenging, and often highly redundant. Research Quest: Can statistical predictions and actions be made cost effectively using the right data management strategies? Yes, by reducing redundancy. J. Bilmes Image and Video Summarization — 12/7/2016 page 14 / 35
  • 14. Bigness Info. in Data Image Summarization Video Summarization End How to identify and measure redundancy? J. Bilmes Image and Video Summarization — 12/7/2016 page 15 / 35
  • 15. Bigness Info. in Data Image Summarization Video Summarization End How to identify and measure redundancy? J. Bilmes Image and Video Summarization — 12/7/2016 page 16 / 35
  • 16. Bigness Info. in Data Image Summarization Video Summarization End Measuring Information in Data What is information? Information Theory (entropy, mutual information) ⇔ probability distributions. Kolmogorov Complexity ⇔ algorithms & models of computation. Information measures over non-random data samples (e.g., images). f( ) = f( , ) < f( , ) < f( , ) J. Bilmes Image and Video Summarization — 12/7/2016 page 18 / 35
  • 17. Bigness Info. in Data Image Summarization Video Summarization End Measuring Information in Data Diminishing returns: The more you have, the less valuable is anything you don’t have. f( )f( )- f( ) - f( ) ≥ J. Bilmes Image and Video Summarization — 12/7/2016 page 19 / 35
  • 18. Bigness Info. in Data Image Summarization Video Summarization End Example: Number of Colors of Balls in Urns Consider an urn containing colored balls. Given a set S of balls, f (S) counts the number of distinct colors. Initial value: 2 (colors in urn). New value with added blue ball: 3 Initial value: 3 (colors in urn). New value with added blue ball: 3 Submodularity : Incremental Value of Object Diminishes in a Larger Context (diminishing returns). Thus, f is submodular. J. Bilmes Image and Video Summarization — 12/7/2016 page 20 / 35
  • 19. Bigness Info. in Data Image Summarization Video Summarization End As the data set size grow . . . There is no data like more data ⇒ more data is like no more data. From Andrew Ng’s Stanford machine learning class, 2011 J. Bilmes Image and Video Summarization — 12/7/2016 page 21 / 35
  • 20. Bigness Info. in Data Image Summarization Video Summarization End As the data set sizes grow . . . 0.70 0.75 0.80 0.85 0.90 0.95 1.00 0.1 1 10 100 1000 Millions of Words TestAccuracy Memory-Based Winnow Perceptron Naïve Bayes Banko & Brill 2001 (Riccardi & Hakkani-Tür, 2005, Speech Recognition) (Callison-Burch&Bloodgood, 2010, Machine Translation) Tong & Koller, 2001 (Soon, Ng, Lim, 2001, Coreference Resolution) 50 100 150 200 250 Number of Training Examples 0 0.2 0.4 0.6 0.8 1 Accuracy (Kadie, 1995, Generic Classification) Sentiment Tutorial, Chris Potts, Stanford Ling., 2011 78 80 82 84 86 88 90 92 700 1.750 3.500 7.000 10.500 14.000 17.500 21.000 Overallaccuracy(%) Training set size SVMs DTs ( Kavzoglu & Colkesen, 2012, Image Classification) Speed, memory, attention, problem solving playing game Luminosity http://www.lumosity.com/blog/how-much-and-how-often-should-i-train/ J. Bilmes Image and Video Summarization — 12/7/2016 page 22 / 35
  • 21. Bigness Info. in Data Image Summarization Video Summarization End Submodularity and Learning Curves Proposition Let V = {1, 2, . . . , n} be a finite ground set, and let f : 2V → R be a set function. If for all permutations σ of V , we have that for all i ≤ j: f (σj |Si−1) ≥ f (σj |Sj−1) (1) with Si = {σ1, σ2, . . . , σi }, then f is submodular. Learning curves might not be exactly submodular, but submodularity seems a reasonable model. J. Bilmes Image and Video Summarization — 12/7/2016 page 23 / 35
  • 22. Bigness Info. in Data Image Summarization Video Summarization End What is Summarization? 1 Start with a massive data set (images, videos, etc.), set V . 2 Identify a good (submodular) information function f (by hand or by machine learning) that represents information in V . 3 Find a subset A ⊆ V of a given size that retains as much information as possible. 4 Luckily, this normally exponential time problem can be done computationally efficiently!! J. Bilmes Image and Video Summarization — 12/7/2016 page 24 / 35
  • 23. Bigness Info. in Data Image Summarization Video Summarization End Modern Image Collections Many images, also that have a higher level gestalt than just a few. J. Bilmes Image and Video Summarization — 12/7/2016 page 26 / 35
  • 24. Bigness Info. in Data Image Summarization Video Summarization End Image Summarization Task: Summarize collection of images by representative subset of the images Applications: Summarizing your holiday pictures. Summarizing image search results Efficient browsing of image collections Video frame summarization Difficulties: No high level ⇓ J. Bilmes Image and Video Summarization — 12/7/2016 page 27 / 35
  • 25. Bigness Info. in Data Image Summarization Video Summarization End Image Summarization - Data Collection Data Statistics 14 image collections with 100 pictures each ∼ 400 human summaries for every image collection, via Amazon Turk, about 5500 summaries total! Example collections: J. Bilmes Image and Video Summarization — 12/7/2016 page 28 / 35
  • 26. Bigness Info. in Data Image Summarization Video Summarization End Image Summarization Whole collection: 3 best summaries: 3 medium summaries: 3 worst summaries: J. Bilmes Image and Video Summarization — 12/7/2016 page 29 / 35
  • 27. Bigness Info. in Data Image Summarization Video Summarization End Image Summarization Typical Results - Learnt mixture using Max-Margin f(∅) = 0 f(V ) = 1 Greedy Min Average Pruned Random Max of Learned Mixture Average Pruned Human Greedy Max Average Pruned Random Average Pruned Human J. Bilmes Image and Video Summarization — 12/7/2016 page 30 / 35
  • 28. Bigness Info. in Data Image Summarization Video Summarization End Real-Time Running Online Video Summarization Live Video Feed Most recent representative video snippet (repeating) Next most recent representative video snippet (repeating) Third most recent representative video snippet (repeating) Fourth most recent representative video snippet (repeating) Least recent representative video snippet (repeating) ... J. Bilmes Image and Video Summarization — 12/7/2016 page 32 / 35
  • 29. Bigness Info. in Data Image Summarization Video Summarization End Real-Time Running Online Video Summarization J. Bilmes Image and Video Summarization — 12/7/2016 page 33 / 35
  • 30. Bigness Info. in Data Image Summarization Video Summarization End The End The End: Thank you! ++ + + f(A) f(B) f(A ∪ B) = f(Ar ) +f(C) + f(Br ) ≥ ≥ = f(A ∩ B) f(A ∩ B) = f(Ar ) + 2f(C) + f(Br ) J. Bilmes Image and Video Summarization — 12/7/2016 page 35 / 35