So sánh phương pháp

	Mạng Perceptron Đa lớp Đa phương thức	Transformer Đa phương thức
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2011 (multimodal extension); 1986 (MLP backpropagation)	2019–2021
Người khởi xướng	Ngiam et al. / Rumelhart, Hinton & Williams (MLP foundations)	Lu et al. (ViLBERT); Radford et al. (CLIP)
Loại	Feedforward neural network with multi-stream fusion	Cross-modal attention-based deep learning model
Công trình gốc	Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 689–696.	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.
Tên gọi khác	MM-MLP, multimodal MLP, multi-input feedforward network, fusion multilayer perceptron	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
Liên quan	5	5
Tóm tắt	A Multimodal Multilayer Perceptron (MM-MLP) is a feedforward neural network that ingests features from two or more heterogeneous input modalities — such as structured tabular data, text embeddings, and image feature vectors — by encoding each stream separately and fusing them into a shared representation before passing it through fully connected layers to produce a classification or regression output.	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.