Machine learningDeep learning / NLP / CV

Multimodalna klasifikacija zasnovana na BERT-u

Multimodalna klasifikacija zasnovana na BERT-u proširuje BERT transformer arhitekturu za zajedničko kodiranje i klasifikaciju podataka iz više modaliteta — najčešće teksta uparenog sa slikama — spajanjem njihovih reprezentacija pre završne klasifikacione glave. Istaknuto predstavljena oko 2019. godine kroz modele kao što su MMBT i ViLBERT, postala je standardni pristup za zadatke gde ni sam tekst ni sama slika ne nose dovoljno informacija za tačno etiketiranje.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

+8 more

Izvori

  1. Kiela, D., Bhooshan, S., Firooz, H., Perez, E., & Testuggine, D. (2019). Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950. link
  2. Lu, J., Batra, D., Parikh, D., & Lee, S. (2019). ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in Neural Information Processing Systems, 32. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Multimodal BERT-based Classification (Transformer Fusion of Text and Non-text Modalities). ScholarGate. https://scholargate.app/sr/deep-learning/multimodal-bert-based-classification

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateMultimodal BERT-based Classification (Multimodal BERT-based Classification (Transformer Fusion of Text and Non-text Modalities)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/multimodal-bert-based-classification · Skup podataka: https://doi.org/10.5281/zenodo.20539026