Semi-Supervised Cross-Modal Retrieval Based on Discriminative Comapping

Figure 3

Precision-recall curves of the proposed MRRDC and compared methods. (a) I2T on wiki-R. (b) T2I on wiki-R. (c) I2T on wiki-W. (d) T2I on wiki-W. (e) I2T on Pascal. (f) T2I on Pascal. (g) I2T on INRIA-Websearch. (h) T2I on INRIA-Websearch.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)