SCENT

SCENT framework uses language guidance to bridge vision and olfactory sensor representations

Researchers introduce SCENT, a multimodal learning framework that uses Vision-Language Models to generate semantic scene descriptors as a bridge between electronic-nose (e-nose) signals and visual/textual representations. A smell encoder is trained to map e-nose signals into a shared embedding space, with a language-guided latent decomposition separating object-specific odors from ambient environmental contributions. Evaluated on the New York Smells dataset, SCENT achieves state-of-the-art cross-modal retrieval on smell-to-image and smell-to-text tasks, outperforming vision-only baselines. The work extends multimodal learning into olfaction, a largely unexplored sensory modality.