EP 3803884 A2 20210414 - METHODS AND APPARATUS FOR MULTI-MODAL PREDICTION USING A TRAINED STATISTICAL MODEL
Title (en)
METHODS AND APPARATUS FOR MULTI-MODAL PREDICTION USING A TRAINED STATISTICAL MODEL
Title (de)
VERFAHREN UND VORRICHTUNG ZUR MULTIMODALEN PRÄDIKTION UNTER VERWENDUNG EINES TRAINIERTEN STATISTISCHEN MODELLS
Title (fr)
PROCÉDÉS ET APPAREIL DE PRÉDICTION MULTIMODALE À L'AIDE D'UN MODÈLE STATISTIQUE APPRIS
Publication
Application
Priority
- US 201862678083 P 20180530
- US 201862678094 P 20180530
- US 2019031260 W 20190508
Abstract (en)
[origin: WO2019231624A2] Methods and apparatus for predicting an association between input data in a first modality and data in a second modality using a statistical model trained to represent interactions between data having a plurality of modalities including the first modality and the second modality, the statistical model comprising a plurality of encoders and decoders, each of which is trained to process data for one of the plurality of modalities, and a joint-modality representation coupling the plurality of encoders and decoders. The method comprises selecting, based on the first modality and the second modality, an encoder/decoder pair or a pair of encoders, from among the plurality of encoders and decoders, and processing the input data with the joint-modality representation and the selected encoder/decoder pair or pair of encoders to predict the association between the input data and the data in the second modality.
IPC 8 full level
G16C 20/30 (2019.01); G16B 5/00 (2019.01); G16B 20/00 (2019.01); G16B 40/20 (2019.01); G16C 20/70 (2019.01)
CPC (source: EP KR)
G16B 5/00 (2019.02 - KR); G16B 20/00 (2019.02 - EP KR); G16B 40/20 (2019.02 - EP KR); G16B 50/00 (2019.02 - KR); G16C 20/30 (2019.02 - EP KR); G16C 20/70 (2019.02 - EP KR); G16B 5/00 (2019.02 - EP)
Designated contracting state (EPC)
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
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
WO 2019231624 A2 20191205; WO 2019231624 A3 20200319; AU 2019276730 A1 20201210; BR 112020023429 A2 20210223; CA 3100065 A1 20191205; CN 112513990 A 20210316; EP 3803884 A2 20210414; JP 2021526259 A 20210930; JP 7490576 B2 20240527; KR 20210018333 A 20210217; MX 2020012899 A 20210226
DOCDB simple family (application)
US 2019031260 W 20190508; AU 2019276730 A 20190508; BR 112020023429 A 20190508; CA 3100065 A 20190508; CN 201980050949 A 20190508; EP 19725548 A 20190508; JP 2020566792 A 20190508; KR 20207037772 A 20190508; MX 2020012899 A 20190508