Table 1:

Results for multimodal sentiment analysis on CMU-MOSI with aligned and non-aligned multimodal sequences. ^h means higher is better and ^l means lower is better. EF stands for early fusion, and LF stands for late fusion.

Metric	${\text{Acc}}_7^h$	${\text{Acc}}_2^h$	F1h	MAEl	Corrh
(Word Aligned) CMU-MOSI Sentiment
EF-LSTM	33.7	75.3	75.2	1.023	0.608
LF-LSTM	35.3	76.8	76.7	1.015	0.625
RMFN (Liang et al., 2018)	38.3	78.4	78.0	0.922	0.681
MFM (Tsai et al., 2019)	36.2	78.1	78.1	0.951	0.662
RAVEN (Wang et al., 2019)	33.2	78.0	76.6	0.915	0.691
MCTN (Pham et al.,2019)	35.6	79.3	79.1	0.909	0.676
MulT (ours)	40.0	83.0	82.8	0.871	0.698
(Unaligned) CMU-MOSI Sentiment
CTC (Graves et al., 2006) + EF-LSTM	31.0	73.6	74.5	1.078	0.542
LF-LSTM	33.7	77.6	77.8	0.988	0.624
CTC + MCTN (Pham et al., 2019)	32.7	75.9	76.4	0.991	0.613
CTC + RAVEN (Wang et al., 2019)	31.7	72.7	73.1	1.076	0.544
MulT (ours)	39.1	81.1	81.0	0.889	0.686