SlideShare a Scribd company logo
Large-scale Semantic Visual Search
NGUYEN ANH TUAN
tuannguyen.research@gmail.com
2016/07/17
About me
• 東京大学 情報理工学系研究科
修士2年生
• テーマ:Object Retrieval,情
報検索等
• 趣味:水泳,囲碁
• ブログ:
https://imsmarxen68.tumblr.co
m/
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
A picture is worth a thousand
words
Outline
• Semantic Visual Search
• A visual search framework
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
Feature
extraction
Feature
aggregation
Feature
matching Re-ranking
Preliminary
results
Final
results
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Visual search
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
Image credits: http://google.com
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
What’s the problem?
• Semantic difficulties: fine-grained differences
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
But for search problem?
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
Query Database
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
But for search problem?
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
Query Database
0.1
0.5
0.2Ranking problem
with a variation of
fine-grained
changes
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
But for search problem?
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
Query Database
0.1
0.5
0.2Find visual representations
to capture all fine-grained
local information in images
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Large-scale Visual Search
Robust feature extraction
• Robust to
– Scale changes
– Rotation and affine changes
– Blur, sharpening, …
Feature
extraction
Feature
aggregation
Feature
matching Re-ranking
Preliminary
results
Final
results
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
A picture is
worth a
thousand words
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Statistical kernels
• Bag-of-Features (BoF)
• Fisher kernel (GMM) [1]
• VLAD (K-means) [2]
Image credits: http://www.mathworks.com/matlabcentral/
Feature
extraction
Feature
aggregation
Feature
matching Re-ranking
Preliminary
results
Final
results
[1] F. Perronnin, C. Dance, “Fisher Kernels on Visual Vocabularies for Image
Categorization,” in Proc. CVPR, IEEE, 2007
[2] H. Jegou, F. Perronnin, M. Douze, J. Sanchez, P. Perez, C. Schmid, “Aggregating Local
Image Descriptors into Compact Codes,” IEEE Trans. Pattern Anal. Mach. Intell. 34 (2012)
1704–1716. NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Statistical kernels
Feature
extraction
Feature
aggregation
Feature
matching Re-ranking
Preliminary
results
Final
results
NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Image matching = Feature matching
• Feature matching→Nearest Neighbor Search
– Inverse Search with Inverted Indices
– Compressed data for better memory usage [3]
Feature
extraction
Feature
aggregation
Feature
matching Re-ranking
Preliminary
results
Final
results
[3] H. Jégou, M. Douze, C. Schmid, Product
quantization for nearest neighbor search., IEEE
Trans. Pattern Anal. Mach. Intell. 33 (2011) 117–
28.Data CompressionNGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Verification
• Geometry verification
– RANSAC methods [4]
– Reduce the number of good inliers
Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html
Feature
extraction
Feature
aggregation
Feature
matching Re-ranking
Preliminary
results
Final
results
[4] M.A. Fischler, R.C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,
Commun. ACM. 24 (1981) 381–395. NGUYEN ANH TUAN 東京大学・情報理
工・修士2年生
Thank you for listening

More Related Content

Viewers also liked

Landset 8 的雲層去除技巧實作
Landset 8 的雲層去除技巧實作Landset 8 的雲層去除技巧實作
Landset 8 的雲層去除技巧實作
鈵斯 倪
 
小魯蛇與他快樂的夥伴
小魯蛇與他快樂的夥伴小魯蛇與他快樂的夥伴
小魯蛇與他快樂的夥伴
鈵斯 倪
 
20150419_pbtech_openstack_nyah #pbtech
20150419_pbtech_openstack_nyah #pbtech20150419_pbtech_openstack_nyah #pbtech
20150419_pbtech_openstack_nyah #pbtech
ume3_
 
LINE Bot 作ってみた
LINE Bot 作ってみたLINE Bot 作ってみた
LINE Bot 作ってみた
Masahiko Yoshikawa
 
ChatOps@研究室
ChatOps@研究室ChatOps@研究室
ChatOps@研究室
Akihiko Horiuchi
 
Slack 簡介
Slack 簡介Slack 簡介
Slack 簡介
Fenix Wu
 
Create Your Own Chatbot with Hubot and CoffeeScript
Create Your Own Chatbot with Hubot and CoffeeScriptCreate Your Own Chatbot with Hubot and CoffeeScript
Create Your Own Chatbot with Hubot and CoffeeScript
Rob Scaduto
 
20170222【ppt】 礦業漏洞又一樁我家地下在挖礦
20170222【ppt】 礦業漏洞又一樁我家地下在挖礦20170222【ppt】 礦業漏洞又一樁我家地下在挖礦
20170222【ppt】 礦業漏洞又一樁我家地下在挖礦
Ray Reng
 
20160717 csc sec_bd
20160717 csc sec_bd20160717 csc sec_bd
20160717 csc sec_bd
寛人 種市
 
DeepLearning 中心に見る最近の論文事情
DeepLearning 中心に見る最近の論文事情DeepLearning 中心に見る最近の論文事情
DeepLearning 中心に見る最近の論文事情
Yuta Yamashita
 
How to build a slack-hubot with js
How to build a slack-hubot with jsHow to build a slack-hubot with js
How to build a slack-hubot with js
Juneyoung Oh
 
正しい開発をする
正しい開発をする正しい開発をする
正しい開発をする
HonMarkHunt
 
【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot
【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot
【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot
s1hit
 
新人研修チーム開発演習発表資料
新人研修チーム開発演習発表資料新人研修チーム開発演習発表資料
新人研修チーム開発演習発表資料
Ryota Sakamoto
 
新日本プロレスに学ぶエンジニアのキャリアプラン
新日本プロレスに学ぶエンジニアのキャリアプラン新日本プロレスに学ぶエンジニアのキャリアプラン
新日本プロレスに学ぶエンジニアのキャリアプラン
HonMarkHunt
 
2015年4月ペパボテックカンファレンス資料
2015年4月ペパボテックカンファレンス資料2015年4月ペパボテックカンファレンス資料
2015年4月ペパボテックカンファレンス資料
buty4649
 
LINE Messaging apiと戯れる
LINE Messaging apiと戯れるLINE Messaging apiと戯れる
LINE Messaging apiと戯れる
HonMarkHunt
 
機械学習を用いた会議診断システムの開発
機械学習を用いた会議診断システムの開発機械学習を用いた会議診断システムの開発
機械学習を用いた会議診断システムの開発
Takahiro Kubo
 
全脳アーキテクチャ実現への長き道のりをいかに支えるのか
全脳アーキテクチャ実現への長き道のりをいかに支えるのか全脳アーキテクチャ実現への長き道のりをいかに支えるのか
全脳アーキテクチャ実現への長き道のりをいかに支えるのか
ドワンゴ 人工知能研究所
 

Viewers also liked (20)

Landset 8 的雲層去除技巧實作
Landset 8 的雲層去除技巧實作Landset 8 的雲層去除技巧實作
Landset 8 的雲層去除技巧實作
 
小魯蛇與他快樂的夥伴
小魯蛇與他快樂的夥伴小魯蛇與他快樂的夥伴
小魯蛇與他快樂的夥伴
 
20150419_pbtech_openstack_nyah #pbtech
20150419_pbtech_openstack_nyah #pbtech20150419_pbtech_openstack_nyah #pbtech
20150419_pbtech_openstack_nyah #pbtech
 
LINE Bot 作ってみた
LINE Bot 作ってみたLINE Bot 作ってみた
LINE Bot 作ってみた
 
ChatOps@研究室
ChatOps@研究室ChatOps@研究室
ChatOps@研究室
 
Slack 簡介
Slack 簡介Slack 簡介
Slack 簡介
 
Create Your Own Chatbot with Hubot and CoffeeScript
Create Your Own Chatbot with Hubot and CoffeeScriptCreate Your Own Chatbot with Hubot and CoffeeScript
Create Your Own Chatbot with Hubot and CoffeeScript
 
20170222【ppt】 礦業漏洞又一樁我家地下在挖礦
20170222【ppt】 礦業漏洞又一樁我家地下在挖礦20170222【ppt】 礦業漏洞又一樁我家地下在挖礦
20170222【ppt】 礦業漏洞又一樁我家地下在挖礦
 
20160717 csc sec_bd
20160717 csc sec_bd20160717 csc sec_bd
20160717 csc sec_bd
 
DeepLearning 中心に見る最近の論文事情
DeepLearning 中心に見る最近の論文事情DeepLearning 中心に見る最近の論文事情
DeepLearning 中心に見る最近の論文事情
 
How to build a slack-hubot with js
How to build a slack-hubot with jsHow to build a slack-hubot with js
How to build a slack-hubot with js
 
正しい開発をする
正しい開発をする正しい開発をする
正しい開発をする
 
【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot
【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot
【JAWS-UG Shimane vol.5 】[ハンズオン]サーバーレスで作るチャットBot
 
新人研修チーム開発演習発表資料
新人研修チーム開発演習発表資料新人研修チーム開発演習発表資料
新人研修チーム開発演習発表資料
 
Python webinar 2nd july
Python webinar 2nd julyPython webinar 2nd july
Python webinar 2nd july
 
新日本プロレスに学ぶエンジニアのキャリアプラン
新日本プロレスに学ぶエンジニアのキャリアプラン新日本プロレスに学ぶエンジニアのキャリアプラン
新日本プロレスに学ぶエンジニアのキャリアプラン
 
2015年4月ペパボテックカンファレンス資料
2015年4月ペパボテックカンファレンス資料2015年4月ペパボテックカンファレンス資料
2015年4月ペパボテックカンファレンス資料
 
LINE Messaging apiと戯れる
LINE Messaging apiと戯れるLINE Messaging apiと戯れる
LINE Messaging apiと戯れる
 
機械学習を用いた会議診断システムの開発
機械学習を用いた会議診断システムの開発機械学習を用いた会議診断システムの開発
機械学習を用いた会議診断システムの開発
 
全脳アーキテクチャ実現への長き道のりをいかに支えるのか
全脳アーキテクチャ実現への長き道のりをいかに支えるのか全脳アーキテクチャ実現への長き道のりをいかに支えるのか
全脳アーキテクチャ実現への長き道のりをいかに支えるのか
 

Similar to 今日から始める人工知能 × 機械学習 Meetup ライトニングトーク1

Image based search engine
Image based search engineImage based search engine
Image based search engine
IRJET Journal
 
Jia-Bin Huang's Curriculum Vitae
Jia-Bin Huang's Curriculum VitaeJia-Bin Huang's Curriculum Vitae
Jia-Bin Huang's Curriculum Vitae
Jia-Bin Huang
 
SUMMER INTERNSHIP PROJECT
SUMMER INTERNSHIP PROJECTSUMMER INTERNSHIP PROJECT
SUMMER INTERNSHIP PROJECTRajarshi Roy
 
Paper id 25201471
Paper id 25201471Paper id 25201471
Paper id 25201471IJRAT
 
Applications of spatial features in cbir a survey
Applications of spatial features in cbir  a surveyApplications of spatial features in cbir  a survey
Applications of spatial features in cbir a survey
csandit
 
APPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEY
APPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEYAPPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEY
APPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEY
cscpconf
 
10.1.1.432.9149
10.1.1.432.914910.1.1.432.9149
10.1.1.432.9149
moemi1
 
10.1.1.432.9149.pdf
10.1.1.432.9149.pdf10.1.1.432.9149.pdf
10.1.1.432.9149.pdf
moemi1
 
https://uii.io/0hIB
https://uii.io/0hIBhttps://uii.io/0hIB
https://uii.io/0hIB
moemi1
 
Predicting Current User Intent with Contextual Markov Models
Predicting Current User Intent with Contextual Markov ModelsPredicting Current User Intent with Contextual Markov Models
Predicting Current User Intent with Contextual Markov Models
Julia Kiseleva
 
An Impact on Content Based Image Retrival A Perspective View
An Impact on Content Based Image Retrival A Perspective ViewAn Impact on Content Based Image Retrival A Perspective View
An Impact on Content Based Image Retrival A Perspective View
ijtsrd
 
Cv huancheng hsu_2018
Cv huancheng hsu_2018Cv huancheng hsu_2018
Cv huancheng hsu_2018
Huan-Cheng Hsu
 
Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...
Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...
Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...
Kalle
 
An Enhance Image Retrieval of User Interest Using Query Specific Approach and...
An Enhance Image Retrieval of User Interest Using Query Specific Approach and...An Enhance Image Retrieval of User Interest Using Query Specific Approach and...
An Enhance Image Retrieval of User Interest Using Query Specific Approach and...
IJSRD
 
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET Journal
 
Official resume titash_mandal_
Official resume titash_mandal_Official resume titash_mandal_
Official resume titash_mandal_
Titash Mandal
 
Active reranking for web image search
Active reranking for web image searchActive reranking for web image search
Active reranking for web image search
ingenioustech
 
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNINGATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
Nathan Mathis
 
Ts2 c topic (1)
Ts2 c topic (1)Ts2 c topic (1)
Ts2 c topic (1)
Harini Vemula
 
Ts2 c topic
Ts2 c topicTs2 c topic
Ts2 c topic
Harini Vemula
 

Similar to 今日から始める人工知能 × 機械学習 Meetup ライトニングトーク1 (20)

Image based search engine
Image based search engineImage based search engine
Image based search engine
 
Jia-Bin Huang's Curriculum Vitae
Jia-Bin Huang's Curriculum VitaeJia-Bin Huang's Curriculum Vitae
Jia-Bin Huang's Curriculum Vitae
 
SUMMER INTERNSHIP PROJECT
SUMMER INTERNSHIP PROJECTSUMMER INTERNSHIP PROJECT
SUMMER INTERNSHIP PROJECT
 
Paper id 25201471
Paper id 25201471Paper id 25201471
Paper id 25201471
 
Applications of spatial features in cbir a survey
Applications of spatial features in cbir  a surveyApplications of spatial features in cbir  a survey
Applications of spatial features in cbir a survey
 
APPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEY
APPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEYAPPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEY
APPLICATIONS OF SPATIAL FEATURES IN CBIR : A SURVEY
 
10.1.1.432.9149
10.1.1.432.914910.1.1.432.9149
10.1.1.432.9149
 
10.1.1.432.9149.pdf
10.1.1.432.9149.pdf10.1.1.432.9149.pdf
10.1.1.432.9149.pdf
 
https://uii.io/0hIB
https://uii.io/0hIBhttps://uii.io/0hIB
https://uii.io/0hIB
 
Predicting Current User Intent with Contextual Markov Models
Predicting Current User Intent with Contextual Markov ModelsPredicting Current User Intent with Contextual Markov Models
Predicting Current User Intent with Contextual Markov Models
 
An Impact on Content Based Image Retrival A Perspective View
An Impact on Content Based Image Retrival A Perspective ViewAn Impact on Content Based Image Retrival A Perspective View
An Impact on Content Based Image Retrival A Perspective View
 
Cv huancheng hsu_2018
Cv huancheng hsu_2018Cv huancheng hsu_2018
Cv huancheng hsu_2018
 
Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...
Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...
Zhang Eye Movement As An Interaction Mechanism For Relevance Feedback In A Co...
 
An Enhance Image Retrieval of User Interest Using Query Specific Approach and...
An Enhance Image Retrieval of User Interest Using Query Specific Approach and...An Enhance Image Retrieval of User Interest Using Query Specific Approach and...
An Enhance Image Retrieval of User Interest Using Query Specific Approach and...
 
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
 
Official resume titash_mandal_
Official resume titash_mandal_Official resume titash_mandal_
Official resume titash_mandal_
 
Active reranking for web image search
Active reranking for web image searchActive reranking for web image search
Active reranking for web image search
 
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNINGATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
 
Ts2 c topic (1)
Ts2 c topic (1)Ts2 c topic (1)
Ts2 c topic (1)
 
Ts2 c topic
Ts2 c topicTs2 c topic
Ts2 c topic
 

Recently uploaded

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
 
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
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
Bhaskar Mitra
 
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
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Product School
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
CatarinaPereira64715
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
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
 
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
 
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
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
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
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
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
 
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
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
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
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 

Recently uploaded (20)

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
 
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...
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
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...
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
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
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
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
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
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
 
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
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
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
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 

今日から始める人工知能 × 機械学習 Meetup ライトニングトーク1

  • 1. Large-scale Semantic Visual Search NGUYEN ANH TUAN tuannguyen.research@gmail.com 2016/07/17
  • 2. About me • 東京大学 情報理工学系研究科 修士2年生 • テーマ:Object Retrieval,情 報検索等 • 趣味:水泳,囲碁 • ブログ: https://imsmarxen68.tumblr.co m/ NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 3. A picture is worth a thousand words
  • 4. Outline • Semantic Visual Search • A visual search framework Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html Feature extraction Feature aggregation Feature matching Re-ranking Preliminary results Final results NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 5. Visual search Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html Image credits: http://google.com NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 6. What’s the problem? • Semantic difficulties: fine-grained differences Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 7. But for search problem? Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html Query Database NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 8. But for search problem? Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html Query Database 0.1 0.5 0.2Ranking problem with a variation of fine-grained changes NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 9. But for search problem? Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html Query Database 0.1 0.5 0.2Find visual representations to capture all fine-grained local information in images NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 11. Robust feature extraction • Robust to – Scale changes – Rotation and affine changes – Blur, sharpening, … Feature extraction Feature aggregation Feature matching Re-ranking Preliminary results Final results Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html A picture is worth a thousand words NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 12. Statistical kernels • Bag-of-Features (BoF) • Fisher kernel (GMM) [1] • VLAD (K-means) [2] Image credits: http://www.mathworks.com/matlabcentral/ Feature extraction Feature aggregation Feature matching Re-ranking Preliminary results Final results [1] F. Perronnin, C. Dance, “Fisher Kernels on Visual Vocabularies for Image Categorization,” in Proc. CVPR, IEEE, 2007 [2] H. Jegou, F. Perronnin, M. Douze, J. Sanchez, P. Perez, C. Schmid, “Aggregating Local Image Descriptors into Compact Codes,” IEEE Trans. Pattern Anal. Mach. Intell. 34 (2012) 1704–1716. NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 14. Image matching = Feature matching • Feature matching→Nearest Neighbor Search – Inverse Search with Inverted Indices – Compressed data for better memory usage [3] Feature extraction Feature aggregation Feature matching Re-ranking Preliminary results Final results [3] H. Jégou, M. Douze, C. Schmid, Product quantization for nearest neighbor search., IEEE Trans. Pattern Anal. Mach. Intell. 33 (2011) 117– 28.Data CompressionNGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 15. Verification • Geometry verification – RANSAC methods [4] – Reduce the number of good inliers Image credits: http://ai.stanford.edu/~jkrause/cars/car_dataset.html Feature extraction Feature aggregation Feature matching Re-ranking Preliminary results Final results [4] M.A. Fischler, R.C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Commun. ACM. 24 (1981) 381–395. NGUYEN ANH TUAN 東京大学・情報理 工・修士2年生
  • 16. Thank you for listening