방법 비교

	Multimodal LDA Topic Model	다중 모달 트랜스포머
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2003	2019–2021
창시자	Blei, D. M. & Jordan, M. I.	Lu et al. (ViLBERT); Radford et al. (CLIP)
유형	Probabilistic generative topic model (multimodal)	Cross-modal attention-based deep learning model
원전	Blei, D. M. & Jordan, M. I. (2003). Modeling annotated data. Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 127–134.	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.
별칭	Multimodal LDA, mm-LDA, multimodal topic model, cross-modal LDA	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
관련	6	5
요약	Multimodal LDA extends Latent Dirichlet Allocation to jointly model multiple data modalities — most often text and images — within a single probabilistic topic framework. Each document or data instance is represented as a mixture of latent topics shared across modalities, enabling the model to discover coherent themes that align visual and linguistic content simultaneously.	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.