方法对比

	多模态门控循环单元 (Multimodal GRU)	门控循环单元 (GRU)
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2014–2017	2014
提出者	Cho, K. et al. (GRU); adapted to multimodal settings by multiple research groups	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
类型	Recurrent neural network (multimodal variant)	Recurrent neural network with gating
开创性文献	Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of EMNLP 2014, 1724–1734.	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014, pp. 1724–1734.
别名	MM-GRU, Multimodal Gated Recurrent Unit, Cross-modal GRU, Multi-input GRU	GRU, GRU network, gated RNN, GRU cell
相关	6	3
摘要	Multimodal GRU extends the Gated Recurrent Unit architecture to jointly process sequential data from multiple input modalities — such as text, audio, and video frames — within a single recurrent framework. By fusing modality-specific encodings at the input or hidden-state level, it captures temporal dependencies across heterogeneous data streams and is widely used in multimodal sentiment analysis, video understanding, and audio-visual speech recognition.	The Gated Recurrent Unit (GRU), introduced by Cho et al. in 2014, is a streamlined recurrent neural network that uses two learned gates — an update gate and a reset gate — to selectively retain or discard information across time steps, enabling effective sequence modelling with fewer parameters than LSTM.