WO2009035108A1 - 対応関係学習装置および方法ならびに対応関係学習用プログラム、アノテーション装置および方法ならびにアノテーション用プログラム、および、リトリーバル装置および方法ならびにリトリーバル用プログラム - Google Patents

対応関係学習装置および方法ならびに対応関係学習用プログラム、アノテーション装置および方法ならびにアノテーション用プログラム、および、リトリーバル装置および方法ならびにリトリーバル用プログラム Download PDF

Info

Publication number
WO2009035108A1
WO2009035108A1 PCT/JP2008/066597 JP2008066597W WO2009035108A1 WO 2009035108 A1 WO2009035108 A1 WO 2009035108A1 JP 2008066597 W JP2008066597 W JP 2008066597W WO 2009035108 A1 WO2009035108 A1 WO 2009035108A1
Authority
WO
WIPO (PCT)
Prior art keywords
program
annotation
retrieval
feature
latent variable
Prior art date
Application number
PCT/JP2008/066597
Other languages
English (en)
French (fr)
Inventor
Tatsuya Harada
Hideki Nakayama
Rie Matsumoto
Yasuo Kuniyoshi
Nobuyuki Otsu
Original Assignee
The University Of Tokyo
National Institute Of Advanced Industrial Science And Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by The University Of Tokyo, National Institute Of Advanced Industrial Science And Technology filed Critical The University Of Tokyo
Priority to US12/733,561 priority Critical patent/US8423485B2/en
Priority to JP2009532255A priority patent/JP5234469B2/ja
Publication of WO2009035108A1 publication Critical patent/WO2009035108A1/ja

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3347—Query execution using vector based model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Library & Information Science (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

画像データ処理システム２０は、画像特徴量ｘiと単語特徴量ｙiとの少なくとも何れか一方に基づいて画像と当該画像に対応した単語とを結びつける抽象的概念Ｌとしての隠れ変数ｓiを導出するために正準相関分析により取得される射影行列ＡおよびＢと、射影行列ＡおよびＢを用いて取得される隠れ変数ｓiと、ある隠れ変数ｓiから任意の画像特徴量ｘが出現する確率Ｐ（ｘ｜ｓi）およびある隠れ変数ｓiから任意の単語特徴量ｙが出現する確率Ｐ（ｙ｜ｓi）とを得るために必要な情報とを記憶した学習用記憶装置４１を有する。これにより、画像特徴量ｘと単語特徴量ｙとが同時に出力する確率Ｐ（ｘ，ｙ）を容易かつ高速に求め、高速かつ精度のよいアノテーションやリトリーバルを実行可能となる。
PCT/JP2008/066597 2007-09-14 2008-09-12 対応関係学習装置および方法ならびに対応関係学習用プログラム、アノテーション装置および方法ならびにアノテーション用プログラム、および、リトリーバル装置および方法ならびにリトリーバル用プログラム WO2009035108A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US12/733,561 US8423485B2 (en) 2007-09-14 2008-09-12 Correspondence learning apparatus and method and correspondence learning program, annotation apparatus and method and annotation program, and retrieval apparatus and method and retrieval program
JP2009532255A JP5234469B2 (ja) 2007-09-14 2008-09-12 対応関係学習装置および方法ならびに対応関係学習用プログラム、アノテーション装置および方法ならびにアノテーション用プログラム、および、リトリーバル装置および方法ならびにリトリーバル用プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2007-240272 2007-09-14
JP2007240272 2007-09-14

Publications (1)

Publication Number Publication Date
WO2009035108A1 true WO2009035108A1 (ja) 2009-03-19

Family

ID=40452114

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2008/066597 WO2009035108A1 (ja) 2007-09-14 2008-09-12 対応関係学習装置および方法ならびに対応関係学習用プログラム、アノテーション装置および方法ならびにアノテーション用プログラム、および、リトリーバル装置および方法ならびにリトリーバル用プログラム

Country Status (3)

Country Link
US (1) US8423485B2 (ja)
JP (1) JP5234469B2 (ja)
WO (1) WO2009035108A1 (ja)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011095531A (ja) * 2009-10-30 2011-05-12 National Institute Of Advanced Industrial Science & Technology Ｈｌａｃ特徴量抽出方法、異常検出方法及び装置
JP2012053848A (ja) * 2010-09-03 2012-03-15 Nippon Telegr & Teleph Corp <Ntt> データ可視化装置、データ変換装置、方法、及びプログラム
JP2012181607A (ja) * 2011-02-28 2012-09-20 Toyota Central R&D Labs Inc 感覚データ識別装置及びプログラム
CN102782678A (zh) * 2010-02-01 2012-11-14 谷歌公司 用于项关联的联合嵌入
JP2014044447A (ja) * 2013-12-09 2014-03-13 National Institute Of Advanced Industrial & Technology 信号特徴抽出装置および信号特徴抽出方法
KR101438114B1 (ko) 2013-02-01 2014-11-03 국방과학연구소 정준상관분석을 이용한 수중표적 식별방법 및 수중표적 식별장치

Families Citing this family (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10210179B2 (en) * 2008-11-18 2019-02-19 Excalibur Ip, Llc Dynamic feature weighting
US20140341443A1 (en) * 2013-05-16 2014-11-20 Microsoft Corporation Joint modeling for facial recognition
CN104572651B (zh) * 2013-10-11 2017-09-29 华为技术有限公司 图片排序方法及装置
US10319035B2 (en) 2013-10-11 2019-06-11 Ccc Information Services Image capturing and automatic labeling system
US9614724B2 (en) 2014-04-21 2017-04-04 Microsoft Technology Licensing, Llc Session-based device configuration
US9639742B2 (en) 2014-04-28 2017-05-02 Microsoft Technology Licensing, Llc Creation of representative content based on facial analysis
US9773156B2 (en) 2014-04-29 2017-09-26 Microsoft Technology Licensing, Llc Grouping and ranking images based on facial recognition data
US9430667B2 (en) 2014-05-12 2016-08-30 Microsoft Technology Licensing, Llc Managed wireless distribution network
US10111099B2 (en) 2014-05-12 2018-10-23 Microsoft Technology Licensing, Llc Distributing content in managed wireless distribution networks
US9384334B2 (en) 2014-05-12 2016-07-05 Microsoft Technology Licensing, Llc Content discovery in managed wireless distribution networks
US9384335B2 (en) 2014-05-12 2016-07-05 Microsoft Technology Licensing, Llc Content delivery prioritization in managed wireless distribution networks
US9874914B2 (en) 2014-05-19 2018-01-23 Microsoft Technology Licensing, Llc Power management contracts for accessory devices
US10037202B2 (en) 2014-06-03 2018-07-31 Microsoft Technology Licensing, Llc Techniques to isolating a portion of an online computing service
US9367490B2 (en) 2014-06-13 2016-06-14 Microsoft Technology Licensing, Llc Reversible connector for accessory devices
US9460493B2 (en) 2014-06-14 2016-10-04 Microsoft Technology Licensing, Llc Automatic video quality enhancement with temporal smoothing and user override
US9373179B2 (en) 2014-06-23 2016-06-21 Microsoft Technology Licensing, Llc Saliency-preserving distinctive low-footprint photograph aging effect
WO2016026135A1 (en) * 2014-08-22 2016-02-25 Microsoft Technology Licensing, Llc Face alignment with shape regression
US11062229B1 (en) * 2016-02-18 2021-07-13 Deepmind Technologies Limited Training latent variable machine learning models using multi-sample objectives
CN105808752B (zh) * 2016-03-10 2018-04-10 大连理工大学 一种基于cca和2pknn的自动图像标注方法
US10157332B1 (en) * 2016-06-06 2018-12-18 A9.Com, Inc. Neural network-based image manipulation
US10489923B2 (en) * 2017-12-13 2019-11-26 Vaisala, Inc. Estimating conditions from observations of one instrument based on training from observations of another instrument
CN108228845B (zh) * 2018-01-09 2020-10-27 华南理工大学 一种手机游戏分类方法
US11669746B2 (en) * 2018-04-11 2023-06-06 Samsung Electronics Co., Ltd. System and method for active machine learning
US10824909B2 (en) * 2018-05-15 2020-11-03 Toyota Research Institute, Inc. Systems and methods for conditional image translation
KR102511996B1 (ko) * 2018-06-26 2023-03-20 에스케이텔레콤 주식회사 준지도 학습 방법
JP7014086B2 (ja) * 2018-08-02 2022-02-01 日本電信電話株式会社 解析装置、解析方法及びプログラム
CN113627176B (zh) * 2021-08-17 2024-04-19 北京计算机技术及应用研究所 一种利用主元分析计算汉语词向量的方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11213131A (ja) * 1998-01-26 1999-08-06 Minolta Co Ltd オブジェクト−キー関連度付与方法およびオブジェクト−キー関連度自動付与装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6070161A (en) 1997-03-19 2000-05-30 Minolta Co., Ltd. Method of attaching keyword or object-to-key relevance ratio and automatic attaching device therefor
US7343296B2 (en) * 2001-03-14 2008-03-11 Puppetools, Inc. Puppetry based communication system, method and internet utility
US7120626B2 (en) * 2002-11-15 2006-10-10 Koninklijke Philips Electronics N.V. Content retrieval based on semantic association
CN100371952C (zh) 2003-04-21 2008-02-27 日本电气株式会社 识别视频图像对象及应用视频图像注释的设备和方法
US20060195858A1 (en) 2004-04-15 2006-08-31 Yusuke Takahashi Video object recognition device and recognition method, video annotation giving device and giving method, and program
DE102005003001B4 (de) * 2005-01-21 2009-10-08 Qimonda Ag Verfahren zur Korrektur des optischen Proximity-Effektes
KR100664964B1 (ko) * 2005-10-11 2007-01-04 삼성전자주식회사 휴대 기기를 제어하는 장치 및 방법
US7536371B2 (en) * 2005-12-05 2009-05-19 Insyst Ltd. Apparatus and method for the analysis of a process having parameter-based faults

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11213131A (ja) * 1998-01-26 1999-08-06 Minolta Co Ltd オブジェクト−キー関連度付与方法およびオブジェクト−キー関連度自動付与装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HARDOON DAVID R ET AL: "A Correlation Approach for Automatic Image Annotation", LECTURE NOTES IN COMPUTER SCIENCE, 2006 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011095531A (ja) * 2009-10-30 2011-05-12 National Institute Of Advanced Industrial Science & Technology Ｈｌａｃ特徴量抽出方法、異常検出方法及び装置
CN102782678A (zh) * 2010-02-01 2012-11-14 谷歌公司 用于项关联的联合嵌入
JP2013519138A (ja) * 2010-02-01 2013-05-23 グーグル インコーポレイテッド アイテム関連付けのための結合埋込
US9110922B2 (en) 2010-02-01 2015-08-18 Google Inc. Joint embedding for item association
JP2012053848A (ja) * 2010-09-03 2012-03-15 Nippon Telegr & Teleph Corp <Ntt> データ可視化装置、データ変換装置、方法、及びプログラム
JP2012181607A (ja) * 2011-02-28 2012-09-20 Toyota Central R&D Labs Inc 感覚データ識別装置及びプログラム
KR101438114B1 (ko) 2013-02-01 2014-11-03 국방과학연구소 정준상관분석을 이용한 수중표적 식별방법 및 수중표적 식별장치
JP2014044447A (ja) * 2013-12-09 2014-03-13 National Institute Of Advanced Industrial & Technology 信号特徴抽出装置および信号特徴抽出方法

Also Published As

Publication number Publication date
US8423485B2 (en) 2013-04-16
JP5234469B2 (ja) 2013-07-10
JPWO2009035108A1 (ja) 2010-12-24
US20110010319A1 (en) 2011-01-13

Similar Documents

Publication Publication Date Title
WO2009035108A1 (ja) 対応関係学習装置および方法ならびに対応関係学習用プログラム、アノテーション装置および方法ならびにアノテーション用プログラム、および、リトリーバル装置および方法ならびにリトリーバル用プログラム
US20200234002A1 (en) Optimization techniques for artificial intelligence
WO2008013621A3 (en) Image management methods, image management systems, and articles of manufacture
EP2068275A3 (en) Communication robot
CA2610208A1 (en) Learning facts from semi-structured text
WO2006015364A3 (en) System and method for data collection and processing
ATE520101T1 (de) Bildverarbeitungsvorrichtung und -verfahren
WO2013019869A3 (en) Data fingerpringting for copy accuracy assurance
CN107368613B (zh) 短文本情感分析方法及装置
CN107004141A (zh) 对大样本组的高效标注
EP2106130A3 (en) Image processing apparatus, image processing method, and program
WO2012070840A3 (ko) 컨센서스 검색 장치 및 방법
WO2014108460A3 (en) A label inspection system and method
WO2012092150A3 (en) Inference engine for video analytics metadata-based event detection and forensic search
GB0616293D0 (en) Method of image processing
EP2450808A3 (en) Semantic visual search engine
CN104142912A (zh) 一种精确的语料类别标注方法及装置
WO2007095589A3 (en) Aggregating and using physical samples
WO2008065598A3 (en) A method, an apparatus and a computer program for data processing
WO2010075155A3 (en) Method and system for searching for information pertaining target objects
EP1978442A3 (en) Program-generating device and method, program for implementing the program-generating method, and storage medium
WO2008103804A3 (en) Iterative region-based automated control point generation
WO2019141289A3 (en) Methods and devices for data traversal
SE1851493A1 (en) Method and system for context- and content aware sensor in a vehicle
GB201006641D0 (en) Method and arrangement relating to a media structure

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 08831045

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2009532255

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 12733561

Country of ref document: US

122 Ep: pct application non-entry in european phase

Ref document number: 08831045

Country of ref document: EP

Kind code of ref document: A1