WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata 事件

WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata arXiv:2602.12819v2 Announce Type: replace-cross Abstract: 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 supports natural-language and reverse-image queries at both the scene level (e.g. empty street) and object level (e.g.