A taxonomy of visual scenes: Typicality ratings and hierarchical classification
- K. Ehinger, A. Torralba, A. Oliva
- Journal of Vision,
This paper presents the first effort to discover and exploit a diverse taxonomy of scene attributes. Starting with the fine-grained SUN database, we perform crowd-sourced human studies to find over 100 attributes that discriminate between scene categories. We construct an attributelabeled dataset on top of the SUN database . This “SUN Attribute database” spans more than 700 categories and 14,000 images and has potential for use in high-level scene understanding, attribute-based hierarchy construction, and fine-grained scene recognition.