AI RESEARCH
WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata
arXiv CS.CV
•
ArXi:2602.12819v2 Announce Type: replace-cross In this paper, we present WISE, an open-source audiovisual search engine which integrates a range of multimodal retrieval capabilities into a single, practical tool accessible to users without machine learning expertise. WISE s natural-language and reverse-image queries at both the scene level (e.g. empty street) and object level (e.g. horse) across images and videos; face-based search for specific individuals; audio retrieval of acoustic events using text (e.g.