Cross-Modal Retrieval (CMR) is a task of retrieving items across different modalities, such as image, text, video, and audio. The core challenge of CMR is the heterogeneity gap, which arises because data from different modalities have distinct representations, making direct comparison difficult. To address this, most CMR methods focus on learning a shared latent embedding space. In this space, concepts from different modalities are projected, allowing their similarity to be measured using a distance metric.
<span class="description-source">Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study</span>