blank Quick help
blank Maintenance news

Scheduled maintenance

Regular maintenance outages:
between 05.00 and 05.15 hrs CET (Monday to Sunday).

Other outages
Availability

2022.02.11

More...
blank News flashes

News Flashes

New version of the European Patent Register – SPC proceedings information in the Unitary Patent Register.

2024-07-24

More...
blank Related links

Extract from the Register of European Patents

EP About this file: EP4004828

EP4004828 - TRAINING METHODS FOR DEEP NETWORKS [Right-click to bookmark this link]
StatusRequest for examination was made
Status updated on  29.04.2022
Database last updated on 25.09.2024
FormerThe international publication has been made
Status updated on  29.01.2021
Most recent event   Tooltip19.06.2024New entry: Renewal fee paid 
Applicant(s)For all designated states
Toyota Research Institute, Inc.
4440 El Camino Real
Los Altos, California 94022 / US
[2022/22]
Inventor(s)01 / STONE, Kevin
4440 El Camino Real
Los Altos, CA 94022 / US
02 / SHANKAR, Krishna
4440 El Camino Real
Los Altos, CA 94022 / US
03 / LASKEY, Michael
4440 El Camino Real
Los Altos, CA 94022 / US
 [2022/22]
Representative(s)D Young & Co LLP
3 Noble Street
London EC2V 7BQ / GB
[N/P]
Former [2022/22]D Young & Co LLP
120 Holborn
London EC1N 2DY / GB
Application number, filing date20844011.505.06.2020
[2022/22]
WO2020US36450
Priority number, dateUS201962877792P23.07.2019         Original published format: US 201962877792 P
US201962877791P23.07.2019         Original published format: US 201962877791 P
US201962877793P23.07.2019         Original published format: US 201962877793 P
US20191657081313.09.2019         Original published format: US201916570813
[2022/22]
Filing languageEN
Procedural languageEN
PublicationType: A1 Application with search report
No.:WO2021015869
Date:28.01.2021
Language:EN
[2021/04]
Type: A1 Application with search report 
No.:EP4004828
Date:01.06.2022
Language:EN
The application published by WIPO in one of the EPO official languages on 28.01.2021 takes the place of the publication of the European patent application.
[2022/22]
Search report(s)International search report - published on:KR28.01.2021
(Supplementary) European search report - dispatched on:EP18.09.2023
ClassificationIPC:G06V20/20, G06V10/82, G06V10/764, G06V10/774, G06N3/08, G06N3/045, G06T13/00, G06T1/00, G06T7/246, H04N13/204, B25J9/16
[2023/28]
CPC:
G06T7/248 (EP,US); B25J9/1605 (CN,US); G06V20/10 (US);
B25J9/1661 (CN,US); B25J9/1664 (CN,US); B25J9/1671 (EP,CN,US);
B25J9/1697 (EP,CN,US); G06F18/214 (CN,US); G06F18/28 (CN,US);
G06N3/08 (EP,CN,US); G06T19/20 (CN,US); G06T7/33 (US);
G06T7/55 (CN,US); G06T7/74 (CN,US); G06V10/751 (US);
G06V10/764 (EP,US); G06V10/774 (EP,US); G06V10/82 (EP,US);
G06V20/20 (EP,US); B25J9/163 (US); B25J9/1666 (EP);
G05B2219/37567 (EP,US); G05B2219/40136 (EP); G05B2219/40543 (EP,US);
G05B2219/40564 (EP,US); G06N20/10 (EP); G06N3/045 (EP);
G06T2200/04 (EP,US); G06T2207/10016 (EP,US); G06T2207/10024 (US);
G06T2207/10028 (EP,US); G06T2207/20081 (EP,US); G06T2207/20084 (EP);
G06T2207/20104 (US) (-)
Former IPC [2022/22]G06N3/08, G06T13/00, G06T1/00, H04N13/204
Designated contracting statesAL,   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 [2022/22]
TitleGerman:TRAININGSVERFAHREN FÜR TIEFE NETZE[2022/22]
English:TRAINING METHODS FOR DEEP NETWORKS[2022/22]
French:PROCÉDÉS D'APPRENTISSAGE DE RÉSEAUX PROFONDS[2022/22]
Entry into regional phase21.01.2022National basic fee paid 
21.01.2022Search fee paid 
21.01.2022Designation fee(s) paid 
21.01.2022Examination fee paid 
Examination procedure21.01.2022Examination requested  [2022/22]
05.04.2024Amendment by applicant (claims and/or description)
05.04.2024Date on which the examining division has become responsible
Fees paidRenewal fee
16.06.2022Renewal fee patent year 03
20.06.2023Renewal fee patent year 04
19.06.2024Renewal fee patent year 05
Opt-out from the exclusive  Tooltip
competence of the Unified
Patent Court
See the Register of the Unified Patent Court for opt-out data
Responsibility for the accuracy, completeness or quality of the data displayed under the link provided lies entirely with the Unified Patent Court.
Documents cited:Search[XP]  - Wald Johanna ET AL, "RIO: 3D Object Instance Re-Localization in Changing Indoor Environments", 2019 IEEE/CVF International Conference on Computer Vision (ICCV), doi:10.1109/ICCV.2019.00775, ISBN 978-1-7281-4803-8, (20190816), pages 7657 - 7666, URL: https://arxiv.org/pdf/1908.06109.pdf, (20230606), XP093052011 [XP] 1-6 * Section 1; Section 3; Section 4;; figures 1, 6, 7, 18 *

DOI:   http://dx.doi.org/10.1109/ICCV.2019.00775
 [A]  - VARGHESE ASHLEY ET AL, ChangeNet: A Deep Learning Architecture for Visual Change Detection, ADVANCES IN DATABASES AND INFORMATION SYSTEMS; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER INTERNATIONAL PUBLISHING, CHAM, PAGE(S) 129 - 145, (20190129), ISBN 978-3-319-10403-4, XP047501655 [A] 1-6 * Section 3;; figures 2-4 *

DOI:   http://dx.doi.org/10.1007/978-3-030-11012-3_10
International search[Y]US2016275376  (KANT SHASHI [US]) [Y] 1-20;
 [A]US2018285697  (SHOTTON JAMIE DANIEL JOSEPH [GB], et al) [A] 1-20;
 [A]US2019102601  (KARPAS LESLIE [US], et al) [A] 1-20;
 [A]US2019130218  (ALBRIGHT EVAN [US], et al) [A] 1-20;
 [A]JP2019096062  (KONICA MINOLTA INC)[A] 1-20;
 [Y]US10332261  (FARIVAR REZA [US], et al) [Y] 1-20
The EPO accepts no responsibility for the accuracy of data originating from other authorities; in particular, it does not guarantee that it is complete, up to date or fit for specific purposes.