方法对比

	多模态Transformer	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	2019–2021	2019
提出者	Lu et al. (ViLBERT); Radford et al. (CLIP)	Kiela, D. et al.; Lu, J. et al.
类型	Cross-modal attention-based deep learning model	Multimodal transformer classifier
开创性文献	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 (NeurIPS), 32.	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 attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer	MMBT, multimodal transformer classification, BERT multimodal fusion, vision-language BERT classifier
相关	5	2
摘要	A 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.	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.