Comparer des méthodes

	LSTM multimodal	Transformeur Multimodal
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2016	2019–2021
Auteur d'origine	Rajagopalan et al. and various concurrent works (2016–2018)	Lu et al. (ViLBERT); Radford et al. (CLIP)
Type	Recurrent neural network architecture	Cross-modal attention-based deep learning model
Source fondatrice	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.
Alias	MM-LSTM, multimodal recurrent network, multi-input LSTM, multimodal sequence model	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
Apparentées	4	5
Résumé	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.