Deep Mamba Multi-modal Learning

TL;DR

This work applies DMML to the field of multimedia retrieval and proposes an innovative Deep Mamba Multi-modal Hashing (DMMH) method that combines the advantages of algorithm accuracy and inference speed.

Abstract

Inspired by the excellent performance of Mamba networks, we propose a novel Deep Mamba Multi-modal Learning (DMML). It can be used to achieve the fusion of multi-modal features. We apply DMML to the field of multimedia retrieval and propose an innovative Deep Mamba Multi-modal Hashing (DMMH) method. It combines the advantages of algorithm accuracy and inference speed. We validated the effectiveness of DMMH on three public datasets and achieved state-of-the-art results.

Figures (2)

• Figure 1: Deep Mamba Multi-modal Learning
• Figure 2: Deep Mamba Multi-modal Hashing