So sánh phương pháp

	Mạng nơ-ron tích chập đa phương thức	Transformer Đa phương thức
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2011	2019–2021
Người khởi xướng	Ngiam, J. et al. / multiple groups	Lu et al. (ViLBERT); Radford et al. (CLIP)
Loại	Multimodal deep learning model	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), 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-CNN, multimodal CNN, multi-input CNN, cross-modal convolutional network	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
Liên quan	5	5
Tóm tắt	A Multimodal Convolutional Neural Network (MM-CNN) processes and fuses two or more input modalities — such as images and text, or video and audio — through dedicated convolutional branches, learning a shared representation that captures complementary signals from each source. The fused representation drives a downstream task such as classification, regression, or retrieval.	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.