ScholarGate
Assistent

Methoden vergleichen

Prüfen Sie die ausgewählten Methoden nebeneinander; abweichende Zeilen sind hervorgehoben.

Multimodaler Transformer×Vision Transformer×
FachgebietDeep LearningDeep Learning
FamilieMachine learningMachine learning
Entstehungsjahr2019–20212021
UrheberLu et al. (ViLBERT); Radford et al. (CLIP)Dosovitskiy, A. et al.
TypCross-modal attention-based deep learning modelTransformer architecture for images (self-attention over patches)
Wegweisende QuelleLu, 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 (NeurIPS), 32. link ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
Aliasnamenmultimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformerGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Verwandt55
ZusammenfassungA Multimodal Transformer extends the standard Transformer architecture to process and jointly reason over two or more input modalities — most commonly text and images, but also audio, video, or structured data. Cross-modal attention layers allow information from one modality to inform representations in another, enabling tasks such as visual question answering, image captioning, and multimodal sentiment analysis.The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).
ScholarGateDatensatz
  1. v1
  2. 2 Quellen
  3. PUBLISHED
  1. v1
  2. 2 Quellen
  3. PUBLISHED

Zur Suche Folien herunterladen

ScholarGateMethoden vergleichen: Multimodal Transformer · Vision Transformer. Abgerufen am 2026-06-18 von https://scholargate.app/de/compare