Published June 12, 2023 | Version v1
Preprint Open

MuseHash: Supervised Bayesian Hashing for Multimodal Image Representation

  • 1. Information Technologies Institute Centre of Research & Technology - Hellas
  • 2. Reykjavik University


This paper presents a novel method for supporting multiple modalities in the field of image retrieval, called Multimodal Bayesian Supervised Hashing (MuseHash). The method takes into consideration the semantic information of the training data through the use of Bayesian regression to estimate the semantic probabilities and statistical properties in the retrieval process. This method is an extension of the previously proposed Bayesian ridge-based Semantic Preserving Hashing (BiasHash) method. Experimentation on various domain-specific and benchmark datasets  demonstrates that MuseHash outperforms six existing state-of-the-art methods in image retrieval performance, regardless of the feature extractor type, code length, and visual or textual descriptors used. This highlights the robustness and adaptability of MuseHash, making it a promising solution for multimodal image retrieval.



Files (2.3 MB)

Name Size Download all
2.3 MB Preview Download

Additional details


CALLISTO – Copernicus Artificial Intelligence Services and data fusion with other distributed data sources and processing at the edge to support DIAS and HPC infrastructures 101004152
European Commission
ISOLA – Innovative & Integrated Security System on Board Covering the Life Cycle of a Passenger Ships Voyage 883302
European Commission