Comparer des méthodes

	Réseau neuronal récurrent multimodal	Réseau de neurones convolutifs multimodaux
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2011–2015	2011
Auteur d'origine	Multiple contributors; prominently Ngiam et al. (2011) and Vinyals et al. (2015)	Ngiam, J. et al. / multiple groups
Type	Multimodal sequence model (recurrent)	Multimodal deep learning model
Source fondatrice	Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015). Show and Tell: A Neural Image Caption Generator. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156–3164.	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.
Alias	MM-RNN, multimodal sequence model, cross-modal RNN, multimodal recurrent encoder-decoder	MM-CNN, multimodal CNN, multi-input CNN, cross-modal convolutional network
Apparentées	6	5
Résumé	A Multimodal Recurrent Neural Network combines inputs from two or more data modalities — such as images, text, and audio — within a recurrent sequence-processing framework. It encodes each modality separately, fuses the representations, and then processes the combined signal through recurrent units (RNN, LSTM, or GRU) to generate or classify sequential outputs. This design made it a foundational approach in image captioning, video description, and audio-visual speech recognition.	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.