JP7163515B2 - ニューラルネットワークのトレーニング方法、ビデオ認識方法及び装置 - Google Patents

ニューラルネットワークのトレーニング方法、ビデオ認識方法及び装置 Download PDF

Info

Publication number
JP7163515B2
JP7163515B2 JP2021570177A JP2021570177A JP7163515B2 JP 7163515 B2 JP7163515 B2 JP 7163515B2 JP 2021570177 A JP2021570177 A JP 2021570177A JP 2021570177 A JP2021570177 A JP 2021570177A JP 7163515 B2 JP7163515 B2 JP 7163515B2
Authority
JP
Japan
Prior art keywords
neural network
directed acyclic
node
acyclic graph
feature map
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.)
Active
Application number
JP2021570177A
Other languages
English (en)
Japanese (ja)
Other versions
JP2022541712A (ja
Inventor
王子豪
林宸
邵▲じん▼
盛律
▲閻▼俊杰
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.)
Shenzhen Sensetime Technology Co Ltd
Original Assignee
Shenzhen Sensetime Technology Co Ltd
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 Shenzhen Sensetime Technology Co Ltd filed Critical Shenzhen Sensetime Technology Co Ltd
Publication of JP2022541712A publication Critical patent/JP2022541712A/ja
Application granted granted Critical
Publication of JP7163515B2 publication Critical patent/JP7163515B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
    • 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
    • G06N3/047—Probabilistic or stochastic networks
    • 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
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
    • 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
    • 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
    • G06V10/84—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using probabilistic graphical models from image or video features, e.g. Markov models or Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/44—Event detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
JP2021570177A 2020-06-19 2021-04-09 ニューラルネットワークのトレーニング方法、ビデオ認識方法及び装置 Active JP7163515B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN202010567864.7A CN111767985B (zh) 2020-06-19 2020-06-19 一种神经网络的训练方法、视频识别方法及装置
CN202010567864.7 2020-06-19
PCT/CN2021/086199 WO2021253938A1 (fr) 2020-06-19 2021-04-09 Procédé et appareil d'apprentissage de réseau neuronal, et procédé et appareil de reconnaissance vidéo

Publications (2)

Publication Number Publication Date
JP2022541712A JP2022541712A (ja) 2022-09-27
JP7163515B2 true JP7163515B2 (ja) 2022-10-31

Family

ID=72721043

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2021570177A Active JP7163515B2 (ja) 2020-06-19 2021-04-09 ニューラルネットワークのトレーニング方法、ビデオ認識方法及び装置

Country Status (5)

Country Link
JP (1) JP7163515B2 (fr)
KR (1) KR20220011208A (fr)
CN (1) CN111767985B (fr)
TW (1) TWI770967B (fr)
WO (1) WO2021253938A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111767985B (zh) * 2020-06-19 2022-07-22 深圳市商汤科技有限公司 一种神经网络的训练方法、视频识别方法及装置
CN112598021A (zh) * 2020-11-27 2021-04-02 西北工业大学 一种基于自动机器学习的图结构搜索方法
WO2024172250A1 (fr) * 2023-02-15 2024-08-22 이화여자대학교 산학협력단 Procédé et appareil d'allègement de réseau d'intelligence artificielle à l'aide d'un niveau de contribution

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018520404A (ja) 2015-04-28 2018-07-26 クゥアルコム・インコーポレイテッドＱｕａｌｃｏｍｍ Ｉｎｃｏｒｐｏｒａｔｅｄ ニューラルネットワークのためのトレーニング基準としてのフィルタ特異性
JP2018170003A (ja) 2017-03-30 2018-11-01 富士通株式会社 ビデオ中のイベントの検出装置、方法及び画像処理装置
JP2020052484A (ja) 2018-09-25 2020-04-02 Ａｗｌ株式会社 物体認識カメラシステム、再学習システム、及び物体認識プログラム

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104281853B (zh) * 2014-09-02 2017-11-17 电子科技大学 一种基于3d卷积神经网络的行为识别方法
US11023523B2 (en) * 2015-10-23 2021-06-01 Carnegie Mellon University Video content retrieval system
US10546211B2 (en) * 2016-07-01 2020-01-28 Google Llc Convolutional neural network on programmable two dimensional image processor
EP3306528B1 (fr) * 2016-10-04 2019-12-25 Axis AB Algorithmes d'analyse destines a fournir des donnees d'apprentissage a des reseaux neuronaux
US11010658B2 (en) * 2017-12-22 2021-05-18 Intel Corporation System and method for learning the structure of deep convolutional neural networks
CN108228861B (zh) * 2018-01-12 2020-09-01 第四范式（北京）技术有限公司 用于执行机器学习的特征工程的方法及系统
CN108334910B (zh) * 2018-03-30 2020-11-03 国信优易数据股份有限公司 一种事件检测模型训练方法以及事件检测方法
CN108985259B (zh) * 2018-08-03 2022-03-18 百度在线网络技术（北京）有限公司 人体动作识别方法和装置
CN109284820A (zh) * 2018-10-26 2019-01-29 北京图森未来科技有限公司 一种深度神经网络的结构搜索方法及装置
US20200167659A1 (en) * 2018-11-27 2020-05-28 Electronics And Telecommunications Research Institute Device and method for training neural network
CN110598598A (zh) * 2019-08-30 2019-12-20 西安理工大学 基于有限样本集的双流卷积神经网络人体行为识别方法
CN110705463A (zh) * 2019-09-29 2020-01-17 山东大学 基于多模态双流3d网络的视频人体行为识别方法及系统
CN110852168A (zh) * 2019-10-11 2020-02-28 西北大学 基于神经架构搜索的行人重识别模型构建方法及装置
CN111767985B (zh) * 2020-06-19 2022-07-22 深圳市商汤科技有限公司 一种神经网络的训练方法、视频识别方法及装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018520404A (ja) 2015-04-28 2018-07-26 クゥアルコム・インコーポレイテッドＱｕａｌｃｏｍｍ Ｉｎｃｏｒｐｏｒａｔｅｄ ニューラルネットワークのためのトレーニング基準としてのフィルタ特異性
JP2018170003A (ja) 2017-03-30 2018-11-01 富士通株式会社 ビデオ中のイベントの検出装置、方法及び画像処理装置
JP2020052484A (ja) 2018-09-25 2020-04-02 Ａｗｌ株式会社 物体認識カメラシステム、再学習システム、及び物体認識プログラム

Also Published As

Publication number Publication date
CN111767985B (zh) 2022-07-22
KR20220011208A (ko) 2022-01-27
JP2022541712A (ja) 2022-09-27
CN111767985A (zh) 2020-10-13
WO2021253938A1 (fr) 2021-12-23
TWI770967B (zh) 2022-07-11
TW202201285A (zh) 2022-01-01

Similar Documents

Publication Publication Date Title
JP7163515B2 (ja) ニューラルネットワークのトレーニング方法、ビデオ認識方法及び装置
US11531889B2 (en) Weight data storage method and neural network processor based on the method
Mishina et al. Boosted random forest
WO2021218517A1 (fr) Procédé permettant d'acquérir un modèle de réseau neuronal et procédé et appareil de traitement d'image
US11144823B1 (en) Method and system for hierarchical weight-sparse convolution processing
US20220108157A1 (en) Hardware architecture for introducing activation sparsity in neural network
CN111382868B (zh) 神经网络结构搜索方法和神经网络结构搜索装置
CN114051615A (zh) 动态处理元件阵列扩展
WO2022057262A1 (fr) Procédé et dispositif de reconnaissance d'image et support de stockage lisible par ordinateur
US9053358B2 (en) Learning device for generating a classifier for detection of a target
JP2019032808A (ja) 機械学習方法および装置
CN108364064A (zh) 操作神经网络的方法、对应网络、装置、以及计算机程序产品
CN115129386A (zh) 用于神经网络部署和执行的有效优化
CN111260020A (zh) 卷积神经网络计算的方法和装置
WO2020236255A1 (fr) Système et procédé pour l'apprentissage incrémental au moyen d'un paradigme de croissance et d'élagage avec des réseaux neuraux
WO2019180314A1 (fr) Réseaux neuronaux artificiels
CN115080138A (zh) 用于神经网络部署和执行的有效存储器使用优化
WO2022063076A1 (fr) Procédé et appareil d'identification d'exemples contradictoires
CN115080139A (zh) 用于神经网络部署和执行的有效量化
Cai et al. Soft and hard filter pruning via dimension reduction
CN114298289A (zh) 一种数据处理的方法、数据处理设备及存储介质
CN113554145B (zh) 确定神经网络的输出的方法、电子设备和计算机程序产品
KR102227437B1 (ko) 연산 가속화가 적용된 신경망 모델의 생성 및 활용을 위한 장치 및 방법
KR20220083782A (ko) 비디오 처리 방법, 장치, 전자 기기, 저장 매체 및 프로그램 제품
KR20220068357A (ko) 딥러닝 객체 검출 처리 장치

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20211125

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20211125

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20221012

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20221019

R150 Certificate of patent or registration of utility model

Ref document number: 7163515

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150