HIGHLIGHTS
SUMMARY
In the era of big data, how to get valuable information from huge and complicated multimodal data is a problem worth focusing on. In contrast, cross-modal retrieval is more convenient and flexible, which can complete information retrieval across different modalities flexibly by mining the association information between pairs of cooccurring cross-modal data; that is, it can return the retrieval results of other modalities related to the query sample according to the sample of any query modality. Subspace learning methods use pairwise cooccurrence information of different modal sample pairs to learn a common . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.