no code implementations • 6 Nov 2020 • Rong-Cheng Tu, Xian-Ling Mao, Rongxin Tu, Binbin Bian, Wei Wei, Heyan Huang
Finally, by minimizing the novel \textit{margin-dynamic-softmax loss}, the modality-specific hashing networks can be trained to generate hash codes which can simultaneously preserve the cross-modal similarity and abundant semantic information well.