@article{18227,
  abstract     = {Existing cross-modal hashing methods ignore the informative multimodal joint information and cannot fully exploit the semantic labels. In this paper, we propose a deep fused two-step cross-modal hashing (DFTH) framework with multiple semantic supervision. In the first step, DFTH learns unified hash codes for instances by a fusion network. Semantic label and similarity reconstruction have been introduced to acquire binary codes that are informative, discriminative and semantic similarity preserving. In the second step, two modality-specific hash networks are learned under the supervision of common hash codes reconstruction, label reconstruction, and intra-modal and inter-modal semantic similarity reconstruction. The modality-specific hash networks can generate semantic preserving binary codes for out-of-sample queries. To deal with the vanishing gradients of binarization, continuous differentiable tanh is introduced to approximate the discrete sign function, making the networks able to back-propagate by automatic gradient computation. Extensive experiments on MIRFlickr25K and NUS-WIDE show the superiority of DFTH over state-of-the-art methods.},
  author       = {Kang, Peipei and Lin, Zehang and Yang, Zhenguo and Bronstein, Alexander and Li, Qing and Liu, Wenyin},
  issn         = {1573-7721},
  journal      = {Multimedia Tools and Applications},
  number       = {11},
  pages        = {15653--15670},
  publisher    = {Springer Nature},
  title        = {{Deep fused two-step cross-modal hashing with multiple semantic supervision}},
  doi          = {10.1007/s11042-022-12187-6},
  volume       = {81},
  year         = {2022},
}