Multimodal Feature Learning for Video Captioning

Table 3

Performance comparison with other state-of-the-art models on MSVD dataset.

Models	B@1	B@2	B@3	B@4	CIDEr
SCN [11]	-	-	-	51.1	77.7
LSTM-TSA [12]	82.8	72.0	62.8	52.8	74.0
hLSTMat [10]	82.9	72.2	63.0	53.0	73.8
SeFLA	84.8	70.8	60.0	50.0	94.3