方法对比

	多模态视觉变换器	多模态BERT分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2021	2019
提出者	Dosovitskiy et al. (ViT); Radford et al. (CLIP multimodal ViT)	Kiela, D. et al.; Lu, J. et al.
类型	Multimodal transformer model	Multimodal transformer classifier
开创性文献	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).	Kiela, D., Bhooshan, S., Firooz, H., Perez, E., & Testuggine, D. (2019). Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950.
别名	Multimodal ViT, vision-language transformer, cross-modal vision transformer, multi-modal ViT	MMBT, multimodal transformer classification, BERT multimodal fusion, vision-language BERT classifier
相关	5	2
摘要	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.	Multimodal BERT-based classification extends the BERT transformer architecture to jointly encode and classify data from multiple modalities — most commonly text paired with images — by fusing their representations before a final classification head. Introduced prominently around 2019 through models such as MMBT and ViLBERT, it has become a standard approach for tasks where neither text nor image alone carries sufficient information for accurate labeling.