SlideShare ist ein Scribd-Unternehmen logo
1 von 19
Downloaden Sie, um offline zu lesen
1 KYOTO UNIVERSITY
KYOTO UNIVERSITY
CLEAR: A Fully User-side Image Search System
Ryoma Sato
2 KYOTO UNIVERSITY
Traditional Services
Service
Develop & Operate
Official Developer
Serve
Twitter
3 KYOTO UNIVERSITY
Problem: each user wants different services
A’s ideal service
Bs’ ideal services
C’s ideal service
D’s ideal service
gap
Actual Service
4 KYOTO UNIVERSITY
User-side systems realize users’ ideals
A’s ideal service
Bs’ ideal services
C’s ideal service
D’s ideal service
Actual Service
User-side systems fill this
gap on the user’s side
5 KYOTO UNIVERSITY
Challenge: users cannot access to the database

Standard IR sysmtes
are implemented by Engineers of
Twitter, who have complete
access to the database.

User-side IR systems
are implemented by users, who don’t have direct access to the database.
Twitter Inc.
Database
Twitter Engineer
IR system
SQL
ANN
Twitter Inc.
Database
User
SQL
Search Query
API
6 KYOTO UNIVERSITY
Flickr provides text search only, no image-based
↑put text here to search for images
Flickr supports tag
and text-based
searches, but no
image-based search
We want to find
images with similar
atmosphere,
similar composition,
and similar colors,
based on images
at hand
7 KYOTO UNIVERSITY
Suppose we have a score function

Suppose we have a function that receives an image
and returns a scalar score

Ex) The more similar a image is to the image at hand,
the higher the score.

Similarity can be calculated based on composition,
color, etc. It is up to the user to decide which one to
use (depending on what the user wants to do).
0.882
8 KYOTO UNIVERSITY
Maximize the score function at hand fron Flickr

Suppose we have a function that receives an image
and returns a scalar score

Problem setup: retrieve (in real time) the image with
the maximum score from all Flickr images when the
score function is passed by the user.
0.882
9 KYOTO UNIVERSITY
Naive methods are intractable

Method 1: A very naive method is to crawl a large
number of images from Flickr, evaluate each one's
score, and return the image with the highest score
→ High communication cost, not finish in real time

Method 2: Pre-crawl and build an index
→ Storage and server costs are high, and is intractable
for an ordinary user.
10 KYOTO UNIVERSITY
Architecture of CLEAR

CLEAR searches images on the fly
CLEAR runs on the frontend
No indices or crawling
No backend servers
11 KYOTO UNIVERSITY
Formulate as a multi-armed bandit problem

Regard the search query as an arm and formulate the
problem as a multi-armed bandit problem
q = dog q = cat q = Persian cat q = goldfish
0.725
Issue a query
reward
...
Score function f
12 KYOTO UNIVERSITY
Demo Video
Demo: https://clear.joisino.net/
13 KYOTO UNIVERSITY
Develop and publish your own search engine

Contribution: An ordinary user realizes a new search
engine for the existing service.

You can easily develop your own search engine.
↔ Traditionally, building search engines requires
a lot of storage, computational, and network
resources.
14 KYOTO UNIVERSITY
CLEAR is general
CLEAR
score function A
content-based
user specifies
the function
15 KYOTO UNIVERSITY
CLEAR is general
CLEAR
score function B
hue-based
you can use
different ones
16 KYOTO UNIVERSITY
CLEAR is general
CLEAR
score function B
hue-based
you can change
the target service
17 KYOTO UNIVERSITY
CLEAR is general
CLEAR
score function B
hue-based
you can change
the target service
18 KYOTO UNIVERSITY
Develop and publish your own search engine

CLEAR is implemented fully on the client’s side
(with JavaScript)

No back-end servers
→ You can realize your own search engine by rewriting
the score function and opening it in a browser.
→ Deployment is easy
You can deploy in on GitHub Pages or Amazon S3.
→ The more people create and publish their own
search systems, the more options there are, and the
easier it will be to find a favorite search system.
↔ Only Flickr official ones and a few voluntary ones.
19 KYOTO UNIVERSITY
Summary: First fully user-side image search

CLEAR is the first practical implementation of
fully user-side image search.

The system is implemented completely on the client-
side (Javascript).

You can build and publish your own search engine.
Code: https://github.com/joisino/clear
Demo: https://clear.joisino.net/
Fork the repository and
build your own search engine!

Weitere ähnliche Inhalte

Ähnlich wie CLEAR: A Fully User-side Image Search System

Android quiz application
Android quiz applicationAndroid quiz application
Android quiz application
MOHDAHMED52
 
J query aosddemo_2004
J query aosddemo_2004J query aosddemo_2004
J query aosddemo_2004
aasishj
 

Ähnlich wie CLEAR: A Fully User-side Image Search System (20)

Reqstr Bplan
Reqstr BplanReqstr Bplan
Reqstr Bplan
 
2015 RESUME July
2015 RESUME July2015 RESUME July
2015 RESUME July
 
IRJET- Hybrid Recommendation System for Movies
IRJET-  	  Hybrid Recommendation System for MoviesIRJET-  	  Hybrid Recommendation System for Movies
IRJET- Hybrid Recommendation System for Movies
 
What Are The Best Practices When Building a Back-end App With Kotlin And Spri...
What Are The Best Practices When Building a Back-end App With Kotlin And Spri...What Are The Best Practices When Building a Back-end App With Kotlin And Spri...
What Are The Best Practices When Building a Back-end App With Kotlin And Spri...
 
openEQUELLA Q3 2018 Quarterly Briefing
openEQUELLA Q3 2018 Quarterly BriefingopenEQUELLA Q3 2018 Quarterly Briefing
openEQUELLA Q3 2018 Quarterly Briefing
 
ravi_das
ravi_dasravi_das
ravi_das
 
AppSphere 15 - How AppDynamics is Shaking up the Synthetic Monitoring Product...
AppSphere 15 - How AppDynamics is Shaking up the Synthetic Monitoring Product...AppSphere 15 - How AppDynamics is Shaking up the Synthetic Monitoring Product...
AppSphere 15 - How AppDynamics is Shaking up the Synthetic Monitoring Product...
 
Microservices for the Masses with Spring Boot and JHipster - Chicago JUG 2018
Microservices for the Masses with Spring Boot and JHipster - Chicago JUG 2018Microservices for the Masses with Spring Boot and JHipster - Chicago JUG 2018
Microservices for the Masses with Spring Boot and JHipster - Chicago JUG 2018
 
Android quiz application
Android quiz applicationAndroid quiz application
Android quiz application
 
Deepika_SSE
Deepika_SSEDeepika_SSE
Deepika_SSE
 
Web crawler with email extractor and image extractor
Web crawler with email extractor and image extractorWeb crawler with email extractor and image extractor
Web crawler with email extractor and image extractor
 
IWMW 2000: A Controversial Proposal
IWMW 2000: A Controversial ProposalIWMW 2000: A Controversial Proposal
IWMW 2000: A Controversial Proposal
 
Bn1 1020 demo android
Bn1 1020 demo  androidBn1 1020 demo  android
Bn1 1020 demo android
 
J query aosddemo_2004
J query aosddemo_2004J query aosddemo_2004
J query aosddemo_2004
 
Movie recommendation Engine using Artificial Intelligence
Movie recommendation Engine using Artificial IntelligenceMovie recommendation Engine using Artificial Intelligence
Movie recommendation Engine using Artificial Intelligence
 
JavaScript for ASP.NET programmers (webcast) upload
JavaScript for ASP.NET programmers (webcast) uploadJavaScript for ASP.NET programmers (webcast) upload
JavaScript for ASP.NET programmers (webcast) upload
 
Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuou...
Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuou...Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuou...
Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuou...
 
Online examination management system..pdf
Online examination management system..pdfOnline examination management system..pdf
Online examination management system..pdf
 
Developing apps faster
Developing apps fasterDeveloping apps faster
Developing apps faster
 
An Introduction to Django Web Framework
An Introduction to Django Web FrameworkAn Introduction to Django Web Framework
An Introduction to Django Web Framework
 

Mehr von joisino

Mehr von joisino (12)

キャッシュオブリビアスアルゴリズム
キャッシュオブリビアスアルゴリズムキャッシュオブリビアスアルゴリズム
キャッシュオブリビアスアルゴリズム
 
Metric Recovery from Unweighted k-NN Graphs
Metric Recovery from Unweighted k-NN GraphsMetric Recovery from Unweighted k-NN Graphs
Metric Recovery from Unweighted k-NN Graphs
 
Private Recommender Systems: How Can Users Build Their Own Fair Recommender S...
Private Recommender Systems: How Can Users Build Their Own Fair Recommender S...Private Recommender Systems: How Can Users Build Their Own Fair Recommender S...
Private Recommender Systems: How Can Users Build Their Own Fair Recommender S...
 
An Introduction to Spectral Graph Theory
An Introduction to Spectral Graph TheoryAn Introduction to Spectral Graph Theory
An Introduction to Spectral Graph Theory
 
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem...
 
最適輸送入門
最適輸送入門最適輸送入門
最適輸送入門
 
ユーザーサイド情報検索システム
ユーザーサイド情報検索システムユーザーサイド情報検索システム
ユーザーサイド情報検索システム
 
最適輸送の解き方
最適輸送の解き方最適輸送の解き方
最適輸送の解き方
 
Random Features Strengthen Graph Neural Networks
Random Features Strengthen Graph Neural NetworksRandom Features Strengthen Graph Neural Networks
Random Features Strengthen Graph Neural Networks
 
Fast Unbalanced Optimal Transport on a Tree
Fast Unbalanced Optimal Transport on a TreeFast Unbalanced Optimal Transport on a Tree
Fast Unbalanced Optimal Transport on a Tree
 
グラフニューラルネットワークとグラフ組合せ問題
グラフニューラルネットワークとグラフ組合せ問題グラフニューラルネットワークとグラフ組合せ問題
グラフニューラルネットワークとグラフ組合せ問題
 
死にたくない
死にたくない死にたくない
死にたくない
 

Kürzlich hochgeladen

Heat Units in plant physiology and the importance of Growing Degree days
Heat Units in plant physiology and the importance of Growing Degree daysHeat Units in plant physiology and the importance of Growing Degree days
Heat Units in plant physiology and the importance of Growing Degree days
Brahmesh Reddy B R
 
Isolation of AMF by wet sieving and decantation method pptx
Isolation of AMF by wet sieving and decantation method pptxIsolation of AMF by wet sieving and decantation method pptx
Isolation of AMF by wet sieving and decantation method pptx
GOWTHAMIM22
 
Quantifying Artificial Intelligence and What Comes Next!
Quantifying Artificial Intelligence and What Comes Next!Quantifying Artificial Intelligence and What Comes Next!
Quantifying Artificial Intelligence and What Comes Next!
University of Hertfordshire
 

Kürzlich hochgeladen (20)

RACEMIzATION AND ISOMERISATION completed.pptx
RACEMIzATION AND ISOMERISATION completed.pptxRACEMIzATION AND ISOMERISATION completed.pptx
RACEMIzATION AND ISOMERISATION completed.pptx
 
GBSN - Biochemistry (Unit 8) Enzymology
GBSN - Biochemistry (Unit 8) EnzymologyGBSN - Biochemistry (Unit 8) Enzymology
GBSN - Biochemistry (Unit 8) Enzymology
 
Heat Units in plant physiology and the importance of Growing Degree days
Heat Units in plant physiology and the importance of Growing Degree daysHeat Units in plant physiology and the importance of Growing Degree days
Heat Units in plant physiology and the importance of Growing Degree days
 
POST TRANSCRIPTIONAL GENE SILENCING-AN INTRODUCTION.pptx
POST TRANSCRIPTIONAL GENE SILENCING-AN INTRODUCTION.pptxPOST TRANSCRIPTIONAL GENE SILENCING-AN INTRODUCTION.pptx
POST TRANSCRIPTIONAL GENE SILENCING-AN INTRODUCTION.pptx
 
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 RpWASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
WASP-69b’s Escaping Envelope Is Confined to a Tail Extending at Least 7 Rp
 
EU START PROJECT. START-Newsletter_Issue_4.pdf
EU START PROJECT. START-Newsletter_Issue_4.pdfEU START PROJECT. START-Newsletter_Issue_4.pdf
EU START PROJECT. START-Newsletter_Issue_4.pdf
 
Virulence Analysis of Citrus canker caused by Xanthomonas axonopodis pv. citr...
Virulence Analysis of Citrus canker caused by Xanthomonas axonopodis pv. citr...Virulence Analysis of Citrus canker caused by Xanthomonas axonopodis pv. citr...
Virulence Analysis of Citrus canker caused by Xanthomonas axonopodis pv. citr...
 
ANALEPTICS Mrs Namrata Sanjay Mane  Department of Pharmaceutical Chemistry...
ANALEPTICS  Mrs Namrata Sanjay  Mane   Department of Pharmaceutical Chemistry...ANALEPTICS  Mrs Namrata Sanjay  Mane   Department of Pharmaceutical Chemistry...
ANALEPTICS Mrs Namrata Sanjay Mane  Department of Pharmaceutical Chemistry...
 
Developing Distributed High-performance Computing Capabilities of an Open Sci...
Developing Distributed High-performance Computing Capabilities of an Open Sci...Developing Distributed High-performance Computing Capabilities of an Open Sci...
Developing Distributed High-performance Computing Capabilities of an Open Sci...
 
Isolation of AMF by wet sieving and decantation method pptx
Isolation of AMF by wet sieving and decantation method pptxIsolation of AMF by wet sieving and decantation method pptx
Isolation of AMF by wet sieving and decantation method pptx
 
Lubrication System in forced feed system
Lubrication System in forced feed systemLubrication System in forced feed system
Lubrication System in forced feed system
 
Manganese‐RichSandstonesasanIndicatorofAncientOxic LakeWaterConditionsinGale...
Manganese‐RichSandstonesasanIndicatorofAncientOxic  LakeWaterConditionsinGale...Manganese‐RichSandstonesasanIndicatorofAncientOxic  LakeWaterConditionsinGale...
Manganese‐RichSandstonesasanIndicatorofAncientOxic LakeWaterConditionsinGale...
 
Adaptive Restore algorithm & importance Monte Carlo
Adaptive Restore algorithm & importance Monte CarloAdaptive Restore algorithm & importance Monte Carlo
Adaptive Restore algorithm & importance Monte Carlo
 
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
dkNET Webinar: The 4DN Data Portal - Data, Resources and Tools to Help Elucid...
 
GBSN - Microbiology (Unit 6) Human and Microbial interaction
GBSN - Microbiology (Unit 6) Human and Microbial interactionGBSN - Microbiology (Unit 6) Human and Microbial interaction
GBSN - Microbiology (Unit 6) Human and Microbial interaction
 
Biochemistry and Biomolecules - Science - 9th Grade by Slidesgo.pptx
Biochemistry and Biomolecules - Science - 9th Grade by Slidesgo.pptxBiochemistry and Biomolecules - Science - 9th Grade by Slidesgo.pptx
Biochemistry and Biomolecules - Science - 9th Grade by Slidesgo.pptx
 
Quantifying Artificial Intelligence and What Comes Next!
Quantifying Artificial Intelligence and What Comes Next!Quantifying Artificial Intelligence and What Comes Next!
Quantifying Artificial Intelligence and What Comes Next!
 
SaffronCrocusGenomicsThessalonikiOnlineMay2024TalkOnline.pptx
SaffronCrocusGenomicsThessalonikiOnlineMay2024TalkOnline.pptxSaffronCrocusGenomicsThessalonikiOnlineMay2024TalkOnline.pptx
SaffronCrocusGenomicsThessalonikiOnlineMay2024TalkOnline.pptx
 
Harry Coumnas Thinks That Human Teleportation is Possible in Quantum Mechanic...
Harry Coumnas Thinks That Human Teleportation is Possible in Quantum Mechanic...Harry Coumnas Thinks That Human Teleportation is Possible in Quantum Mechanic...
Harry Coumnas Thinks That Human Teleportation is Possible in Quantum Mechanic...
 
MSCII_ FCT UNIT 5 TOXICOLOGY.pdf
MSCII_              FCT UNIT 5 TOXICOLOGY.pdfMSCII_              FCT UNIT 5 TOXICOLOGY.pdf
MSCII_ FCT UNIT 5 TOXICOLOGY.pdf
 

CLEAR: A Fully User-side Image Search System

  • 1. 1 KYOTO UNIVERSITY KYOTO UNIVERSITY CLEAR: A Fully User-side Image Search System Ryoma Sato
  • 2. 2 KYOTO UNIVERSITY Traditional Services Service Develop & Operate Official Developer Serve Twitter
  • 3. 3 KYOTO UNIVERSITY Problem: each user wants different services A’s ideal service Bs’ ideal services C’s ideal service D’s ideal service gap Actual Service
  • 4. 4 KYOTO UNIVERSITY User-side systems realize users’ ideals A’s ideal service Bs’ ideal services C’s ideal service D’s ideal service Actual Service User-side systems fill this gap on the user’s side
  • 5. 5 KYOTO UNIVERSITY Challenge: users cannot access to the database  Standard IR sysmtes are implemented by Engineers of Twitter, who have complete access to the database.  User-side IR systems are implemented by users, who don’t have direct access to the database. Twitter Inc. Database Twitter Engineer IR system SQL ANN Twitter Inc. Database User SQL Search Query API
  • 6. 6 KYOTO UNIVERSITY Flickr provides text search only, no image-based ↑put text here to search for images Flickr supports tag and text-based searches, but no image-based search We want to find images with similar atmosphere, similar composition, and similar colors, based on images at hand
  • 7. 7 KYOTO UNIVERSITY Suppose we have a score function  Suppose we have a function that receives an image and returns a scalar score  Ex) The more similar a image is to the image at hand, the higher the score.  Similarity can be calculated based on composition, color, etc. It is up to the user to decide which one to use (depending on what the user wants to do). 0.882
  • 8. 8 KYOTO UNIVERSITY Maximize the score function at hand fron Flickr  Suppose we have a function that receives an image and returns a scalar score  Problem setup: retrieve (in real time) the image with the maximum score from all Flickr images when the score function is passed by the user. 0.882
  • 9. 9 KYOTO UNIVERSITY Naive methods are intractable  Method 1: A very naive method is to crawl a large number of images from Flickr, evaluate each one's score, and return the image with the highest score → High communication cost, not finish in real time  Method 2: Pre-crawl and build an index → Storage and server costs are high, and is intractable for an ordinary user.
  • 10. 10 KYOTO UNIVERSITY Architecture of CLEAR  CLEAR searches images on the fly CLEAR runs on the frontend No indices or crawling No backend servers
  • 11. 11 KYOTO UNIVERSITY Formulate as a multi-armed bandit problem  Regard the search query as an arm and formulate the problem as a multi-armed bandit problem q = dog q = cat q = Persian cat q = goldfish 0.725 Issue a query reward ... Score function f
  • 12. 12 KYOTO UNIVERSITY Demo Video Demo: https://clear.joisino.net/
  • 13. 13 KYOTO UNIVERSITY Develop and publish your own search engine  Contribution: An ordinary user realizes a new search engine for the existing service.  You can easily develop your own search engine. ↔ Traditionally, building search engines requires a lot of storage, computational, and network resources.
  • 14. 14 KYOTO UNIVERSITY CLEAR is general CLEAR score function A content-based user specifies the function
  • 15. 15 KYOTO UNIVERSITY CLEAR is general CLEAR score function B hue-based you can use different ones
  • 16. 16 KYOTO UNIVERSITY CLEAR is general CLEAR score function B hue-based you can change the target service
  • 17. 17 KYOTO UNIVERSITY CLEAR is general CLEAR score function B hue-based you can change the target service
  • 18. 18 KYOTO UNIVERSITY Develop and publish your own search engine  CLEAR is implemented fully on the client’s side (with JavaScript)  No back-end servers → You can realize your own search engine by rewriting the score function and opening it in a browser. → Deployment is easy You can deploy in on GitHub Pages or Amazon S3. → The more people create and publish their own search systems, the more options there are, and the easier it will be to find a favorite search system. ↔ Only Flickr official ones and a few voluntary ones.
  • 19. 19 KYOTO UNIVERSITY Summary: First fully user-side image search  CLEAR is the first practical implementation of fully user-side image search.  The system is implemented completely on the client- side (Javascript).  You can build and publish your own search engine. Code: https://github.com/joisino/clear Demo: https://clear.joisino.net/ Fork the repository and build your own search engine!