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: EP4030352

EP4030352 - TASK-SPECIFIC TEXT GENERATION BASED ON MULTIMODAL INPUTS [Right-click to bookmark this link]
StatusRequest for examination was made
Status updated on  07.10.2022
Database last updated on 16.11.2024
FormerThe application has been published
Status updated on  17.06.2022
Most recent event   Tooltip20.12.2023New entry: Renewal fee paid 
Applicant(s)For all designated states
Facebook, Inc.
1601 Willow Road
Menlo Park, CA 94025 / US
[2022/29]
Inventor(s)01 / LIN, Xudong
Menlo Park, 94025 / US
02 / BERTASIUS, Gediminas
Menlo Park, 94025 / US
03 / WANG, Jue
Menlo Park, 94025 / US
04 / PARIKH, Devi Niru
Menlo Park, 94025 / US
05 / TORRESANI, Lorenzo
Menlo Park, 94025 / US
 [2022/29]
Representative(s)Murgitroyd & Company
165-169 Scotland Street
Glasgow G5 8PL / GB
[N/P]
Former [2022/29]Murgitroyd & Company
Murgitroyd House
165-169 Scotland Street
Glasgow G5 8PL / GB
Application number, filing date21216259.821.12.2021
[2022/29]
Priority number, dateUS202163135456P08.01.2021         Original published format: US 202163135456 P
US20211733975904.06.2021         Original published format: US202117339759
[2022/29]
Filing languageEN
Procedural languageEN
PublicationType: A1 Application with search report 
No.:EP4030352
Date:20.07.2022
Language:EN
[2022/29]
Search report(s)(Supplementary) European search report - dispatched on:EP15.06.2022
ClassificationIPC:G06N3/04, G06N3/08
[2022/29]
CPC:
G06N3/084 (EP,CN,US); G06F16/3329 (CN); G06F40/284 (US);
G06F16/35 (CN); G06F40/242 (CN); G06F40/30 (CN,US);
G06N3/045 (EP); G06N3/048 (EP,CN); G06N7/01 (US) (-)
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 [2022/45]
Former [2022/29]AL,  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 
Extension statesBANot yet paid
MENot yet paid
Validation statesKHNot yet paid
MANot yet paid
MDNot yet paid
TNNot yet paid
TitleGerman:AUFGABENSPEZIFISCHE TEXTERZEUGUNG BASIEREND AUF MULTIMODALEN EINGABEN[2022/29]
English:TASK-SPECIFIC TEXT GENERATION BASED ON MULTIMODAL INPUTS[2022/29]
French:GÉNÉRATION DE TEXTE SPÉCIFIQUE À UNE TÂCHE BASÉE SUR DES ENTRÉES MULTIMODALES[2022/29]
Examination procedure04.10.2022Amendment by applicant (claims and/or description)
04.10.2022Examination requested  [2022/45]
04.10.2022Date on which the examining division has become responsible
Fees paidRenewal fee
20.12.2023Renewal fee patent year 03
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[XI]  - LINJIE LI ET AL, "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20200929), XP081774033 [X] 1-5,13-15 * abstract * * page 2 - page 9 * * page 13 - page 18 * [I] 6-12
 [XP]  - LIN XUDONG ET AL, "VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs", 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), doi:10.1109/CVPR46437.2021.00693, ISBN 978-1-6654-4509-2, (20210128), pages 7001 - 7011, URL: https://arxiv.org/pdf/2101.12059v1.pdf, (20220607), XP055928720 [XP] 1-15 * the whole document *

DOI:   http://dx.doi.org/10.1109/CVPR46437.2021.00693
 [A]  - GABRIEL HUANG ET AL, "Multimodal Pretraining for Dense Video Captioning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20201110), XP081821068 [A] 1-15 * the whole document *
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.