Comparer des méthodes

	Mécanisme d'attention	LSTM	Transformeur Multimodal
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2015	1997	2019–2021
Auteur d'origine	Bahdanau, D.; Luong, M.T.	Hochreiter, S. & Schmidhuber, J.	Lu et al. (ViLBERT); Radford et al. (CLIP)
Type	Neural attention layer (encoder-decoder)	Recurrent neural network (gated memory cell)	Cross-modal attention-based deep learning model
Source fondatrice	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.	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	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
Apparentées	5	5	5
Résumé	The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector.	LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps.	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.