方法对比

	多模态循环神经网络	多模态BERT分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2011–2015	2019
提出者	Multiple contributors; prominently Ngiam et al. (2011) and Vinyals et al. (2015)	Kiela, D. et al.; Lu, J. et al.
类型	Multimodal sequence model (recurrent)	Multimodal transformer classifier
开创性文献	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.	Kiela, D., Bhooshan, S., Firooz, H., Perez, E., & Testuggine, D. (2019). Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950.
别名	MM-RNN, multimodal sequence model, cross-modal RNN, multimodal recurrent encoder-decoder	MMBT, multimodal transformer classification, BERT multimodal fusion, vision-language BERT classifier
相关	6	2
摘要	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.	Multimodal BERT-based classification extends the BERT transformer architecture to jointly encode and classify data from multiple modalities — most commonly text paired with images — by fusing their representations before a final classification head. Introduced prominently around 2019 through models such as MMBT and ViLBERT, it has become a standard approach for tasks where neither text nor image alone carries sufficient information for accurate labeling.