# Central Similarity Multi-View Hashing for Multimedia Retrieval

arXiv: https://arxiv.org/abs/2308.13774 · HTML: https://mlsanity.com/paper/2308.13774/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 26 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [Deep Metric Multi-View Hashing for Multimedia Retrieval](https://mlsanity.com/paper/2304.06358/) (2023)

## Built on by (most cited first, 3 of 3)

- [Trusted Mamba Contrastive Network for Multi-View Clustering](https://mlsanity.com/paper/2412.16487/) (2024)
- [Adaptive Confidence Multi-View Hashing for Multimedia Retrieval](https://mlsanity.com/paper/2312.07327/) (2023)
- [CLIP Multi-modal Hashing for Multimedia Retrieval](https://mlsanity.com/paper/2410.07783/) (2024)

## Abstract (arXiv)

Hash representation learning of multi-view heterogeneous data is the key to improving the accuracy of multimedia retrieval. However, existing methods utilize local similarity and fall short of deeply fusing the multi-view features, resulting in poor retrieval accuracy. Current methods only use local similarity to train their model. These methods ignore global similarity. Furthermore, most recent works fuse the multi-view features via a weighted sum or concatenation. We contend that these fusion methods are insufficient for capturing the interaction between various views. We present a novel Central Similarity Multi-View Hashing (CSMVH) method to address the mentioned problems. Central similarity learning is used for solving the local similarity problem, which can utilize the global similarity between the hash center and samples. We present copious empirical data demonstrating the superiority of gate-based fusion over conventional approaches. On the MS COCO and NUS-WIDE, the proposed CSMVH performs better than the state-of-the-art methods by a large margin (up to 11.41% mean Average Precision (mAP) improvement).