# Deep Binary Reconstruction for Cross-modal Hashing

arXiv: https://arxiv.org/abs/1708.05127 · HTML: https://mlsanity.com/paper/1708.05127/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2017.

## Built on by (most cited first, 6 of 6)

- [Accelerating Code Search with Deep Hashing and Code Classification](https://mlsanity.com/paper/2203.15287/) (2022)
- [Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing](https://mlsanity.com/paper/2112.06489/) (2021)
- [Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search](https://mlsanity.com/paper/2202.04327/) (2022)
- [Efficient Cross-Modal Retrieval via Deep Binary Hashing and Quantization](https://mlsanity.com/paper/2202.10232/) (2022)
- [Deep Lifelong Cross-modal Hashing](https://mlsanity.com/paper/2304.13357/) (2023)
- [FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environments](https://mlsanity.com/paper/2504.09941/) (2025)

## Abstract (arXiv)

With the increasing demand of massive multimodal data storage and organization, cross-modal retrieval based on hashing technique has drawn much attention nowadays. It takes the binary codes of one modality as the query to retrieve the relevant hashing codes of another modality. However, the existing binary constraint makes it difficult to find the optimal cross-modal hashing function. Most approaches choose to relax the constraint and perform thresholding strategy on the real-value representation instead of directly solving the original objective. In this paper, we first provide a concrete analysis about the effectiveness of multimodal networks in preserving the inter- and intra-modal consistency. Based on the analysis, we provide a so-called Deep Binary Reconstruction (DBRC) network that can directly learn the binary hashing codes in an unsupervised fashion. The superiority comes from a proposed simple but efficient activation function, named as Adaptive Tanh (ATanh). The ATanh function can adaptively learn the binary codes and be trained via back-propagation. Extensive experiments on three benchmark datasets demonstrate that DBRC outperforms several state-of-the-art methods in both image2text and text2image retrieval task.