EP3500978A4 - Verfahren und vorrichtung für zero-shot-lernen - Google Patents

Verfahren und vorrichtung für zero-shot-lernen Download PDF

Info

Publication number
EP3500978A4
EP3500978A4 EP16913114.1A EP16913114A EP3500978A4 EP 3500978 A4 EP3500978 A4 EP 3500978A4 EP 16913114 A EP16913114 A EP 16913114A EP 3500978 A4 EP3500978 A4 EP 3500978A4
Authority
EP
European Patent Office
Prior art keywords
zero
shot learning
shot
learning
Prior art date
Legal status (The legal status 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 status listed.)
Withdrawn
Application number
EP16913114.1A
Other languages
English (en)
French (fr)
Other versions
EP3500978A1 (de
Inventor
Yunlong YU
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nokia Technologies Oy
Original Assignee
Nokia Technologies Oy
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 Nokia Technologies Oy filed Critical Nokia Technologies Oy
Publication of EP3500978A1 publication Critical patent/EP3500978A1/de
Publication of EP3500978A4 publication Critical patent/EP3500978A4/de
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
EP16913114.1A 2016-08-16 2016-08-16 Verfahren und vorrichtung für zero-shot-lernen Withdrawn EP3500978A4 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/095512 WO2018032354A1 (en) 2016-08-16 2016-08-16 Method and apparatus for zero-shot learning

Publications (2)

Publication Number Publication Date
EP3500978A1 EP3500978A1 (de) 2019-06-26
EP3500978A4 true EP3500978A4 (de) 2020-01-22

Family

ID=61196222

Family Applications (1)

Application Number Title Priority Date Filing Date
EP16913114.1A Withdrawn EP3500978A4 (de) 2016-08-16 2016-08-16 Verfahren und vorrichtung für zero-shot-lernen

Country Status (3)

Country Link
EP (1) EP3500978A4 (de)
CN (1) CN109643384A (de)
WO (1) WO2018032354A1 (de)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110580501B (zh) * 2019-08-20 2023-04-25 天津大学 一种基于变分自编码对抗网络的零样本图像分类方法
CN112418257B (zh) * 2019-08-22 2023-04-18 四川大学 一种有效的基于潜在视觉属性挖掘的零样本学习方法
CN110826638B (zh) * 2019-11-12 2023-04-18 福州大学 基于重复注意力网络的零样本图像分类模型及其方法
CN111914903B (zh) * 2020-07-08 2022-10-25 西安交通大学 一种基于外分布样本检测的广义零样本目标分类方法、装置及相关设备
CN112380374B (zh) * 2020-10-23 2022-11-18 华南理工大学 一种基于语义扩充的零样本图像分类方法
CN114627312B (zh) * 2022-05-17 2022-09-06 中国科学技术大学 零样本图像分类方法、系统、设备及存储介质
CN116051909B (zh) * 2023-03-06 2023-06-16 中国科学技术大学 一种直推式零次学习的未见类图片分类方法、设备及介质
CN116109877B (zh) * 2023-04-07 2023-06-20 中国科学技术大学 组合式零样本图像分类方法、系统、设备及存储介质
CN117541882B (zh) * 2024-01-05 2024-04-19 南京信息工程大学 一种基于实例的多视角视觉融合转导式零样本分类方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103164713B (zh) * 2011-12-12 2016-04-06 阿里巴巴集团控股有限公司 图像分类方法和装置
US20130251340A1 (en) * 2012-03-21 2013-09-26 Wei Jiang Video concept classification using temporally-correlated grouplets
CN103400160B (zh) * 2013-08-20 2017-03-01 中国科学院自动化研究所 一种零训练样本行为识别方法
CN103646256A (zh) * 2013-12-17 2014-03-19 上海电机学院 一种基于图像特征稀疏重构的图像分类方法
CN105184260B (zh) * 2015-09-10 2019-03-08 北京大学 一种图像特征提取方法及行人检测方法及装置
CN105512679A (zh) * 2015-12-02 2016-04-20 天津大学 一种基于极限学习机的零样本分类方法
CN105701514B (zh) * 2016-01-15 2019-05-21 天津大学 一种用于零样本分类的多模态典型相关分析的方法
CN105718940B (zh) * 2016-01-15 2019-03-29 天津大学 基于多组间因子分析的零样本图像分类方法
CN105740879B (zh) * 2016-01-15 2019-05-21 天津大学 基于多模态判别分析的零样本图像分类方法

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
FARHADI A ET AL: "Describing objects by their attributes", 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION : CVPR 2009 ; MIAMI [BEACH], FLORIDA, USA, 20 - 25 JUNE 2009, IEEE, PISCATAWAY, NJ, 20 June 2009 (2009-06-20), pages 1778 - 1785, XP031607299, ISBN: 978-1-4244-3992-8 *
FU ZHENYONG ET AL: "Zero-shot object recognition by semantic manifold distance", 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE, 7 June 2015 (2015-06-07), pages 2635 - 2644, XP032793709, DOI: 10.1109/CVPR.2015.7298879 *
LIU MINGXIA ET AL: "Attribute relation learning for zero-shot classification", NEUROCOMPUTING, ELSEVIER, AMSTERDAM, NL, vol. 139, 3 April 2014 (2014-04-03), pages 34 - 46, XP029024275, ISSN: 0925-2312, DOI: 10.1016/J.NEUCOM.2013.09.056 *
See also references of WO2018032354A1 *

Also Published As

Publication number Publication date
EP3500978A1 (de) 2019-06-26
CN109643384A (zh) 2019-04-16
WO2018032354A1 (en) 2018-02-22

Similar Documents

Publication Publication Date Title
EP3470044A4 (de) Navigationsvorrichtung und -verfahren
EP3337361A4 (de) Speichervorrichtung und steuerungsverfahren dafür
EP3293993A4 (de) Verfahren und vorrichtung zur bereitstellung eines profils
EP3338272A4 (de) Anzeigevorrichtung und steuerungsverfahren dafür
EP3218900A4 (de) Verfahren und vorrichtung zur bereitstellung von sprachanwendungstests
EP3267348A4 (de) Verfahren und vorrichtung zur erkennung eines risikoverhaltens
EP3227667A4 (de) Testvorrichtung und steuerungsverfahren dafür
EP3500978A4 (de) Verfahren und vorrichtung für zero-shot-lernen
EP3455471A4 (de) Vorrichtung und verfahren
EP3640819A4 (de) Suchverfahren und -vorrichtung
EP3401103A4 (de) Aufzeichnungsverfahren und aufzeichnungsvorrichtung
EP3411323A4 (de) Zweiblockschutz-messvorrichtung und verfahren
EP3290150A4 (de) Baugruppenherstellungsvorrichtung und baugruppenherstellungsverfahren
EP3549002A4 (de) Verfahren und vorrichtung für gefühlsbasierte interaktion
EP3185507A4 (de) Zugangssteuerungsverfahren und -vorrichtung
EP3540113A4 (de) Bekleidungsbehandlungsvorrichtung und verfahren zur steuerung der bekleidungsbehandlungsvorrichtung
EP3524136A4 (de) Mikroskopvorrichtung und steuerungsverfahren
EP3080996A4 (de) Vorrichtung und verfahren zur bereitstellung von informationen
EP3382923A4 (de) Strahlentrainingsverfahren und -vorrichtung
EP3119120A4 (de) Vorrichtung und verfahren
EP3104764A4 (de) Sichttrainingsverfahren und vorrichtung
EP3271179A4 (de) Druckvorrichtung und druckverfahren
EP3104659A4 (de) Vorrichtung und verfahren
EP3494643A4 (de) Verfahren und vorrichtung zur synchronisierung
EP3385738A4 (de) Prüfvorrichtung und steuerungsverfahren dafür

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20190130

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: NOKIA TECHNOLOGIES OY

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
A4 Supplementary search report drawn up and despatched

Effective date: 20200103

RIC1 Information provided on ipc code assigned before grant

Ipc: G06K 9/46 20060101ALI20191218BHEP

Ipc: G06K 9/66 20060101AFI20191218BHEP

Ipc: G06K 9/62 20060101ALI20191218BHEP

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20200801