手法を比較

	アテンションメカニズム	マルチモーダル・トランスフォーマー
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2015	2019–2021
提唱者	Bahdanau, D.; Luong, M.T.	Lu et al. (ViLBERT); Radford et al. (CLIP)
種類	Neural attention layer (encoder-decoder)	Cross-modal attention-based deep learning model
原典	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	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.
別名	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
関連	5	5
概要	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.	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.