Extract from the Register of European Patents

EP About this file: EP4047553

EP4047553 - MOTION COMPENSATION AND REFINEMENT IN RECURRENT NEURAL NETWORKS [Right-click to bookmark this link]
StatusThe application is deemed to be withdrawn
Status updated on  17.10.2025
Database last updated on 18.03.2026
FormerExamination is in progress
Status updated on  06.03.2025
FormerRequest for examination was made
Status updated on  22.07.2022
Most recent event   Tooltip17.10.2025Application deemed to be withdrawnpublished on 19.11.2025  [2025/47]
Applicant(s)For all designated states
Aptiv Technologies AG
Spitalstrasse 5
8200 Schaffhausen / CH
[2024/39]
Former [2024/27]For all designated states
Aptiv Technologies AG
Pestalozzistrasse 2
8200 Schaffhausen / CH
Former [2023/13]For all designated states
Aptiv Technologies Limited
The Financial Services Centre
Bishop's Court Hill
St. Michael / BB
Former [2022/34]For all designated states
Aptiv Technologies Limited
Erin Court
Bishop's Court Hill
14004 St. Michael / BB
Inventor(s)01 / Kossaczký, Igor
42117 Wuppertal / BB
02 / Labusch, Sven
50737 Köln / BB
03 / Meuter, Mirko
40699 Erkrath / BB
 [2022/34]
Representative(s)Bardehle Pagenberg Partnerschaft mbB Patentanwälte Rechtsanwälte
Prinzregentenplatz 7
81675 München / DE
[N/P]
Former [2022/34]Hoffmann Eitle
Patent- und Rechtsanwälte PartmbB
Arabellastraße 30
81925 München / DE
Application number, filing date21158127.719.02.2021
[2022/34]
Filing languageEN
Procedural languageEN
PublicationType: A1 Application with search report 
No.:EP4047553
Date:24.08.2022
Language:EN
[2022/34]
Search report(s)(Supplementary) European search report - dispatched on:EP06.08.2021
ClassificationIPC:G06T7/20
[2022/34]
CPC:
G06T7/20 (EP); G06N3/044 (EP,CN,US); G06N3/0442 (EP);
G06N3/0464 (EP); G06N3/084 (EP,CN); G06N3/09 (EP);
G06V10/82 (US); G06V20/58 (US); G07C5/085 (US);
G06T2207/20081 (EP); G06T2207/20084 (EP) (-)
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 [2022/34]
Extension statesBANot yet paid
MENot yet paid
Validation statesKHNot yet paid
MANot yet paid
MDNot yet paid
TNNot yet paid
TitleGerman:BEWEGUNGSKOMPENSATION UND -VERFEINERUNG IN WIEDERKEHRENDEN NEURONALEN NETZEN[2022/34]
English:MOTION COMPENSATION AND REFINEMENT IN RECURRENT NEURAL NETWORKS[2022/34]
French:COMPENSATION ET DÉCOMPOSITION DE MOUVEMENT DANS DES RÉSEAUX NEURONAUX RÉCURRENTS[2022/34]
Examination procedure19.02.2021Examination requested  [2022/34]
27.01.2023Amendment by applicant (claims and/or description)
27.01.2023Date on which the examining division has become responsible
05.03.2025Despatch of a communication from the examining division (Time limit: M04)
08.07.2025Application deemed to be withdrawn, date of legal effect  [2025/47]
23.07.2025Despatch of communication that the application is deemed to be withdrawn, reason: reply to the communication from the examining division not received in time  [2025/47]
Fees paidRenewal fee
09.02.2023Renewal fee patent year 03
16.02.2024Renewal fee patent year 04
25.02.2025Renewal 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[XAI]   MASHA ITKINA ET AL: "Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 28 April 2019 (2019-04-28), XP081268191
 [A]   AREND HINTZE ET AL: "The structure of evolved representations across different substrates for artificial intelligence", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 5 April 2018 (2018-04-05), XP080867748
Examination  NUSS DOMINIK ET AL: "A random finite set approach for dynamic occupancy grid maps with real-time application", THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, vol. 37, no. 8, 1 July 2018 (2018-07-01), pages 841 - 866, XP055921798, Retrieved from the Internet DOI: 10.1177/0278364918775523

DOI:   http://dx.doi.org/10.1177/0278364918775523
   GANG CHEN: "A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 8 October 2016 (2016-10-08), XP081351523
by applicantUS7639171
 US9470777
 EP3454079
   HOCHREITER ET AL.: "Long short-term memory", NEURAL COMPUTATION, vol. 9, no. 8, 1997, pages 1735 - 1780, XP055232921, DOI: 10.1162/neco.1997.9.8.1735

DOI:   http://dx.doi.org/10.1162/neco.1997.9.8.1735
   XINGJIAN ET AL.: "Convolutional LSTM network: A machine learning approach for precipitation nowcasting", ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS,, 2015, pages 802 - 810
   JADERBERG ET AL.: "Spatial transformer networks", ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, 2015, pages 2017 - 2025
   PATRAUCEAN ET AL.: "Spatiotemporal video autoencoder with differentiable memory", ARXIV PREPRINT ARXIV:1511.06309, 2015
   NILSSON ET AL.: "Semantic video segmentation by gated recurrent flow propagation", PROCEEDINGS OF THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2018, pages 6819 - 6828, XP033473600, DOI: 10.1109/CVPR.2018.00713

DOI:   http://dx.doi.org/10.1109/CVPR.2018.00713
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.