Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Saturday 31.10.2020 at 7:00 AM CET
Settings

Settings

Goto Application

1. WO2020192869 - FEATURE EXTRACTION AND RETRIEVAL IN VIDEOS

Publication Number WO/2020/192869
Publication Date 01.10.2020
International Application No. PCT/EP2019/057259
International Filing Date 22.03.2019
IPC
G06K 9/00 2006.01
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 9/62 2006.01
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 9/00718
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
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
00718Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
G06K 9/6267
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
G06K 9/629
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
629of extracted features
G06K 9/6293
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
6293of classification results relating to different input data, e.g. multimodal recognition
Applicants
  • HUAWEI TECHNOLOGIES CO., LTD. [CN]/[CN]
  • REDZIC, Milan [RS]/[DE] (US)
Inventors
  • REDZIC, Milan
  • TANG, Jian
  • HU, Feiyan
  • MOHEDANO, Eva
  • MCGUINNESS, Kevin
  • O'CONNOR, Noel
  • SMEATON, Alan
Agents
  • KREUZ, Georg
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) FEATURE EXTRACTION AND RETRIEVAL IN VIDEOS
(FR) EXTRACTION ET RÉCUPÉRATION DE CARACTÉRISTIQUES DANS DES VIDÉOS
Abstract
(EN)
A device for processing a video stream, the device being configured to: receive a visual data stream and an audio data stream; extract features from the visual and audio data streams to form a set of visual frame features and a set of audio frame features respectively; aggregate the set of visual frame features and the set of audio frame features to form visual and audio compact representations respectively, wherein the video compact representation is formed using compact bilinear pooling; and concatenate the visual and audio compact representations to form a compact audio-visual feature representation.
(FR)
L'invention concerne un dispositif permettant de traiter un flux vidéo, le dispositif étant configuré afin : de recevoir un flux de données visuelles et un flux de données audio ; d'extraire des caractéristiques des flux de données visuelles et audio afin de former un ensemble de caractéristiques de trames visuelles et un ensemble de caractéristiques de trames audio respectivement ; d'agréger l'ensemble de caractéristiques de trames visuelles et l'ensemble de caractéristiques de trame audio afin de former des représentations compactes visuelles et audio respectivement, la représentation compacte vidéo étant formée à l'aide d'un regroupement bilinéaire compact ; et de concaténer les représentations compactes visuelles et audio afin de former une représentation de caractéristiques audio-visuelles compacte.
Latest bibliographic data on file with the International Bureau