MX2021002777A - Redes neuronales ventrodorsales: deteccion de objetos mediante atencion selectiva. - Google Patents

Redes neuronales ventrodorsales: deteccion de objetos mediante atencion selectiva.

Info

Publication number
MX2021002777A
MX2021002777A MX2021002777A MX2021002777A MX2021002777A MX 2021002777 A MX2021002777 A MX 2021002777A MX 2021002777 A MX2021002777 A MX 2021002777A MX 2021002777 A MX2021002777 A MX 2021002777A MX 2021002777 A MX2021002777 A MX 2021002777A
Authority
MX
Mexico
Prior art keywords
ventral
visual
object detection
neural networks
detection via
Prior art date
Application number
MX2021002777A
Other languages
English (en)
Inventor
Yen- Yun Yu
Jack Reese
Azadeh Moghtaderi
Mohammad K Ebrahimpour
Jiayun Li
Original Assignee
Ancestry Com Operations Inc
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 Ancestry Com Operations Inc filed Critical Ancestry Com Operations Inc
Publication of MX2021002777A publication Critical patent/MX2021002777A/es

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F18/24133—Distances to prototypes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • 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
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • 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
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Medical Informatics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Algebra (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Image Analysis (AREA)

Abstract

Las realizaciones descritas en este documento se refieren en general a una metodología de clasificación eficaz de objetos dentro de un medio visual. La metodología utiliza una primera red neuronal para realizar una localización de objetos basada en la atención dentro de un medio visual para generar una máscara visual. La máscara visual se aplica al medio visual para generar un medio visual enmascarado. El medio visual enmascarado puede luego alimentarse a una segunda red neuronal para detectar y clasificar objetos dentro del medio visual.
MX2021002777A 2018-09-21 2019-09-19 Redes neuronales ventrodorsales: deteccion de objetos mediante atencion selectiva. MX2021002777A (es)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201862734897P 2018-09-21 2018-09-21
US16/573,180 US10796152B2 (en) 2018-09-21 2019-09-17 Ventral-dorsal neural networks: object detection via selective attention
PCT/US2019/051868 WO2020061273A1 (en) 2018-09-21 2019-09-19 Ventral-dorsal neural networks: object detection via selective attention

Publications (1)

Publication Number Publication Date
MX2021002777A true MX2021002777A (es) 2021-03-25

Family

ID=69883219

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2021002777A MX2021002777A (es) 2018-09-21 2019-09-19 Redes neuronales ventrodorsales: deteccion de objetos mediante atencion selectiva.

Country Status (10)

Country Link
US (3) US10796152B2 (es)
EP (1) EP3853777A4 (es)
CN (1) CN112805717A (es)
AU (1) AU2019345266B2 (es)
BR (1) BR112021005214A2 (es)
CA (1) CA3110708A1 (es)
IL (1) IL281530A (es)
MX (1) MX2021002777A (es)
NZ (1) NZ773328A (es)
WO (1) WO2020061273A1 (es)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102018213056A1 (de) * 2018-08-03 2020-02-06 Robert Bosch Gmbh Verfahren und Vorrichtung zum Ermitteln einer Erklärungskarte
US10796152B2 (en) * 2018-09-21 2020-10-06 Ancestry.Com Operations Inc. Ventral-dorsal neural networks: object detection via selective attention
US11869032B2 (en) * 2019-10-01 2024-01-09 Medixin Inc. Computer system and method for offering coupons
CN111985504B (zh) * 2020-08-17 2021-05-11 中国平安人寿保险股份有限公司 基于人工智能的翻拍检测方法、装置、设备及介质
CN112258557B (zh) * 2020-10-23 2022-06-10 福州大学 一种基于空间注意力特征聚合的视觉跟踪方法
US11842540B2 (en) * 2021-03-31 2023-12-12 Qualcomm Incorporated Adaptive use of video models for holistic video understanding
CN113255759B (zh) * 2021-05-20 2023-08-22 广州广电运通金融电子股份有限公司 基于注意力机制的目标内特征检测系统、方法和存储介质

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006000103A1 (en) * 2004-06-29 2006-01-05 Universite De Sherbrooke Spiking neural network and use thereof
EP2263150A2 (en) * 2008-02-27 2010-12-22 Tsvi Achler Feedback systems and methods for recognizing patterns
WO2010105988A1 (en) * 2009-03-20 2010-09-23 Semeion Centro Ricerche Natural computational machine
US20150379708A1 (en) 2010-12-07 2015-12-31 University Of Iowa Research Foundation Methods and systems for vessel bifurcation detection
US20160225053A1 (en) * 2015-01-29 2016-08-04 Clear Research Corporation Mobile visual commerce system
US10210418B2 (en) * 2016-07-25 2019-02-19 Mitsubishi Electric Research Laboratories, Inc. Object detection system and object detection method
DE102016216795A1 (de) 2016-09-06 2018-03-08 Audi Ag Verfahren zur Ermittlung von Ergebnisbilddaten
US11580398B2 (en) 2016-10-14 2023-02-14 KLA-Tenor Corp. Diagnostic systems and methods for deep learning models configured for semiconductor applications
US10380741B2 (en) * 2016-12-07 2019-08-13 Samsung Electronics Co., Ltd System and method for a deep learning machine for object detection
EP3589191A4 (en) * 2017-03-02 2020-11-11 Spectral MD Inc. AUTOMATIC LEARNING SYSTEMS AND TECHNIQUES FOR MULTISPECTRAL ANALYSIS OF AMPUTATION SITES
US20200085382A1 (en) 2017-05-30 2020-03-19 Arterys Inc. Automated lesion detection, segmentation, and longitudinal identification
US11704790B2 (en) * 2017-09-26 2023-07-18 Washington University Supervised classifier for optimizing target for neuromodulation, implant localization, and ablation
US11004209B2 (en) 2017-10-26 2021-05-11 Qualcomm Incorporated Methods and systems for applying complex object detection in a video analytics system
JP7118622B2 (ja) * 2017-11-16 2022-08-16 株式会社Preferred Networks 物体検出装置、物体検出方法及びプログラム
US10354122B1 (en) * 2018-03-02 2019-07-16 Hong Kong Applied Science and Technology Research Institute Company Limited Using masks to improve classification performance of convolutional neural networks with applications to cancer-cell screening
US10332261B1 (en) * 2018-04-26 2019-06-25 Capital One Services, Llc Generating synthetic images as training dataset for a machine learning network
US10304193B1 (en) * 2018-08-17 2019-05-28 12 Sigma Technologies Image segmentation and object detection using fully convolutional neural network
US10796152B2 (en) * 2018-09-21 2020-10-06 Ancestry.Com Operations Inc. Ventral-dorsal neural networks: object detection via selective attention

Also Published As

Publication number Publication date
US20200097723A1 (en) 2020-03-26
US11475658B2 (en) 2022-10-18
US20200410235A1 (en) 2020-12-31
US20210174083A1 (en) 2021-06-10
CA3110708A1 (en) 2020-03-26
IL281530A (en) 2021-05-31
AU2019345266B2 (en) 2024-04-18
EP3853777A1 (en) 2021-07-28
WO2020061273A1 (en) 2020-03-26
AU2019345266A1 (en) 2021-03-18
BR112021005214A2 (pt) 2021-06-08
US10949666B2 (en) 2021-03-16
CN112805717A (zh) 2021-05-14
NZ773328A (en) 2021-02-16
US10796152B2 (en) 2020-10-06
EP3853777A4 (en) 2022-06-22

Similar Documents

Publication Publication Date Title
MX2021002777A (es) Redes neuronales ventrodorsales: deteccion de objetos mediante atencion selectiva.
MX2020013412A (es) Sistemas y metodos para entrenar redes generativas antagonicas y uso de redes generativas antagonicas entrenadas.
EP3935507A4 (en) NEAR REAL-TIME DETECTION AND CLASSIFICATION OF MACHINE FAULTS USING MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE
MX2018000673A (es) Red neuronal profunda convolucional recurrente para deteccion de objetos.
WO2020132102A3 (en) Neural networks for coarse- and fine-object classifications
EP3888336A4 (en) SYSTEM AND METHODS FOR PEER GROUP DETECTION, VISUALIZATION AND ANALYSIS IN ARTIFICIAL INTELLIGENCE SYSTEMS FOR IDENTITY MANAGEMENT USING CLUSTER-BASED NETWORK IDENTITY GRAPH ANALYSIS
MX2018001483A (es) Sistemas y metodos para detectar tornados.
MX2018009566A (es) Sistema y metodo para la visualizacion y caracterizacion de objetos en imagenes.
EP3897021A3 (en) Techniques to manage integrity protection
SG10201802739PA (en) Neural network systems
MX2019000222A (es) Sistemas y metodos para identificar contenido coincidente.
GB201208921D0 (en) Detection of intermodulation products
IN2014DE00692A (es)
MX2017014588A (es) Deteccion de follaje mediante el uso de datos de intervalo.
GB2571388A (en) A vehicle tracker for monitoring operation of a vehicle and method thereof
MX2021003238A (es) Tecnologias de accion basadas en la deteccion de objetos.
ZA202004143B (en) Systems for dynamic light detection obscuration and methods for using thereof
CN106781195A (zh) 一种煤矿火灾烟雾监测系统
WO2019043458A3 (en) SUPER-RESOLUTION METROLOGY METHODS BASED ON SINGULAR DISTRIBUTIONS AND DEEP LEARNING
CN205121295U (zh) 人体esd智能监控系统
BR112015017106A2 (pt) Método implementado por computador para detectar palavras-chave predeterminadas em um fluxo de áudio e sistema para detectar palavras-chave predeterminadas em um fluxo de áudio
MX357643B (es) Metodo y dispositivo para activar una operacion especificada.
MX2020006223A (es) Tecnicas analiticas de ubicacion.
SE1750903A1 (en) Fall detection system and method
IL243825B (en) A system and method for automated forensic investigation