방법 비교

	다중 모드 GRU	Long Short-Term Memory (LSTM)
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2014–2017	1997
창시자	Cho, K. et al. (GRU); adapted to multimodal settings by multiple research groups	Hochreiter, S. & Schmidhuber, J.
유형	Recurrent neural network (multimodal variant)	Recurrent neural network with gated memory cells
원전	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.	Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
별칭	MM-GRU, Multimodal Gated Recurrent Unit, Cross-modal GRU, Multi-input GRU	LSTM, LSTM network, LSTM-RNN, long short-term memory RNN
관련	6	4
요약	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.	Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step.