So sánh phương pháp

	Transformer Thị giác Đa phương thức	Transformer Thị giác
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2021	2021
Người khởi xướng	Dosovitskiy et al. (ViT); Radford et al. (CLIP multimodal ViT)	Dosovitskiy, A. et al.
Loại	Multimodal transformer model	Transformer architecture for images (self-attention over patches)
Công trình gốc	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations (ICLR).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Tên gọi khác	Multimodal ViT, vision-language transformer, cross-modal vision transformer, multi-modal ViT	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Liên quan	5	5
Tóm tắt	Multimodal Vision Transformer (Multimodal ViT) extends the Vision Transformer architecture to jointly process and align representations from multiple modalities — typically images and text — using self-attention and cross-attention mechanisms. By learning shared or aligned embedding spaces across modalities, it enables tasks such as visual question answering, image-text retrieval, visual grounding, and image captioning.	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).