方法对比

	多模态自然语言处理	Vision Transformer
领域	文本挖掘	深度学习
方法族	Process / pipeline	Machine learning
起源年份	2021 (modern era, CLIP onward)	2021
提出者	Radford et al. (OpenAI) — CLIP, 2021; Li et al. — BLIP-2, 2023	Dosovitskiy, A. et al.
类型	Cross-modal understanding and generation pipeline	Transformer architecture for images (self-attention over patches)
开创性文献	Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning (ICML), 8748–8763.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
别名	Çok Kipli NLP (Multimodal NLP), vision-language models, multimodal learning	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
相关	4	5
摘要	Multimodal NLP is a family of natural-language-processing pipelines that combine text with one or more additional data modalities — most commonly images, but also audio and video — to perform understanding and generation tasks such as visual question answering, image captioning, and multimodal sentiment recognition. The field gained its modern form with CLIP (Radford et al., 2021) and has since advanced through architectures such as BLIP-2 (Li et al., 2023) that bridge frozen image encoders and large language models.	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).