Combining Holistic and Part-based Deep Representations for Computational Painting Categorization
ICMR, pp. 339-342, 2016.
Automatic analysis of visual art, such as paintings, is a challenging inter-disciplinary research problem. Conventional approaches only rely on global scene characteristics by encoding holistic information for computational painting categorization. We argue that such approaches are sub-optimal and that discriminative common visual structu...More
Full Text (Upload PDF)
PPT (Upload PPT)