방법 비교

	다중 양식 LSTM	다중 모달 트랜스포머
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2016	2019–2021
창시자	Rajagopalan et al. and various concurrent works (2016–2018)	Lu et al. (ViLBERT); Radford et al. (CLIP)
유형	Recurrent neural network architecture	Cross-modal attention-based deep learning model
원전	Rajagopalan, S., Tran, L., Rozgic, V., Narayanan, S., Kumar, A., & Ramakrishna, S. (2016). Extending Long Short-Term Memory for Multi-View Structured Learning. In Proceedings of ECCV 2016. Springer.	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	MM-LSTM, multimodal recurrent network, multi-input LSTM, multimodal sequence model	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
관련	4	5
요약	Multimodal LSTM extends the standard Long Short-Term Memory network to jointly process sequential data from multiple input modalities — such as text, audio, and video — within a unified recurrent architecture. By fusing representations from different sources before or within the LSTM cells, it captures temporal dependencies that span and cross modalities, making it a foundational approach for tasks like sentiment analysis, video captioning, and affective computing.	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.