方法对比

	多模态Doc2Vec	多模态Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2014–2017	2019–2021
提出者	Le, Q. V. & Mikolov, T. (Doc2Vec core); multimodal extensions by various authors post-2014	Lu et al. (ViLBERT); Radford et al. (CLIP)
类型	Multimodal document embedding	Cross-modal attention-based deep learning model
开创性文献	Le, Q. V., & Mikolov, T. (2014). Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning (ICML), PMLR 32(2), 1188–1196.	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.
别名	Multimodal Paragraph Vector, Cross-modal Doc2Vec, Multi-source PV-DM, Multimodal Document Embedding	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
相关	6	5
摘要	Multimodal Doc2Vec extends the Doc2Vec paragraph-vector framework to incorporate information from more than one modality — typically text alongside images, audio, or structured metadata — producing a shared document-level embedding that captures semantics from multiple sources simultaneously. It is used for cross-modal retrieval, multi-source classification, and document representation where text alone is insufficient.	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.