Improving Visual-Semantic Embeddings by Learning Semantically-Enhanced Hard Negatives for Cross-modal Information Retrieval
Authors: Gong, Y. and Cosma, G.
http://dx.doi.org/10.1016/j.patcog.2022.109272
Source: arXiv
Authors: Gong, Y. and Cosma, G.
http://dx.doi.org/10.1016/j.patcog.2022.109272
Source: arXiv