Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021097378 - CONTEXT-DRIVEN LEARNING OF HUMAN-OBJECT INTERACTIONS

Publication Number WO/2021/097378
Publication Date 20.05.2021
International Application No. PCT/US2020/060626
International Filing Date 14.11.2020
IPC
G06K 9/00 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/46 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6274
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
6274based on distances to neighbourhood prototypes, e.g. Restricted Coulomb Energy Networks
G06K 9/6292
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6288Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
6292of classification results, e.g. of classification results related to same input data
G06V 10/454
G06V 10/82
G06V 20/00
Applicants
  • QUALCOMM TECHNOLOGIES, INC. [US]/[US]
Inventors
  • KILICKAYA, Mert
  • HUSSEIN, Noureldien Mahmoud Elsayed
  • GAVVES, Efstratios
  • SMEULDERS, Arnold Wilhelmus Maria
Agents
  • LENKIN, Alan M.
  • LUTZ, Joseph
  • PARTOW-NAVID, Puya
  • CROSBY, Cornell D.
Priority Data
2019010051515.11.2019GR
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) CONTEXT-DRIVEN LEARNING OF HUMAN-OBJECT INTERACTIONS
(FR) APPRENTISSAGE GUIDÉ PAR CONTEXTE D'INTERACTIONS HUMAIN-OBJET
Abstract
(EN) A method for classifying a human-object interaction includes identifying a human-object interaction in the input. Context features of the input are identified. Each identified context feature is compared with the identified human-object interaction. An importance of the identified context feature is determined for the identified human-object interaction. The context feature is fused with the identified human-object interaction when the importance is greater than a threshold.
(FR) Procédé de classification d'une interaction humain-objet qui comprend l'identification d'une interaction humain-objet dans l'entrée. Des caractéristiques de contexte de l'entrée sont identifiées. Chaque caractéristique de contexte identifiée est comparée à l'interaction humain-objet identifiée. Une importance de la caractéristique contextuelle identifiée est déterminée pour l'interaction humain-objet identifiée. La caractéristique de contexte est fusionnée avec l'interaction humain-objet identifiée lorsque l'importance est supérieure à un seuil.
Latest bibliographic data on file with the International Bureau