ST-Sem: A Multimodal Method for Points-of-Interest Classification Using Street-Level Imagery

Street-level imagery contains a variety of visual information about the facades of Points of Interest (POIs). In addition to general mor- phological features, signs on the facades of, primarily, business-related POIs could be a valuable source of information about the type and iden- tity of a POI. Recent advancements in computer vision could leverage visual information from street-level imagery, and contribute to the classification of POIs. However, there is currently a gap in existing literature regarding the use of visual labels contained in street-level imagery, where their value as indicators of POI categories is assessed. This paper presents Scene-Text Semantics (ST-Sem), a novel method that leverages visual la- bels (e.g., texts, logos) from street-level imagery as complementary in- formation for the categorization of business-related POIs. Contrary to existing methods that fuse visual and textual information at a feature- level, we propose a late fusion approach that combines visual and textual cues after resolving issues of incorrect digitization and semantic ambiguity of the retrieved textual components. Experiments on two existing and a newly-created datasets show that ST-Sem can outperform visual-only approaches by 80% and related multimodal approaches by 4%.