手法を比較

	マルチモーダルDoc2Vec	マルチモーダルBERTベース分類
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2014–2017	2019
提唱者	Le, Q. V. & Mikolov, T. (Doc2Vec core); multimodal extensions by various authors post-2014	Kiela, D. et al.; Lu, J. et al.
種類	Multimodal document embedding	Multimodal transformer classifier
原典	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.	Kiela, D., Bhooshan, S., Firooz, H., Perez, E., & Testuggine, D. (2019). Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950.
別名	Multimodal Paragraph Vector, Cross-modal Doc2Vec, Multi-source PV-DM, Multimodal Document Embedding	MMBT, multimodal transformer classification, BERT multimodal fusion, vision-language BERT classifier
関連	6	2
概要	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.	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.