[Retracted] A Multimodal Model for College English Teaching Using Text and Image Feature Extraction

Table 2

Performance comparison of the cross-modal retrieval methods on Flickr30K dataset.

Algorithm model	Image retrieval			Sentence retrieval
R@K	1	10	20	1	10	20
Random ranking	7.1	15.6	19.8	6.9	14.9	20.3
SDT-RNN	7.5	25.3	26.7	6.9	34.7	40.2
Deep fragment	8.1	36.9	49.3	10.1	35.7	46.3
MCNN	26.3	29.6	49.1	29.3	18.5	67.1
Proposed	32.1	49.2	72.3	37.9	65.1	75.5