Hierarchical bag-of-words model for joint multi-view object representation and classification

Multi-view object classification is a challenging problem in image retrieval. One common approach is to apply the visual bag-of-words (BoW) model to all view representations of each object class and compare them with the representation of the query image one by one so as to determine the closest view of the object class. This approach offers good matching performance, yet it demands a large amount of computation and storage space. To address these issues, we propose a novel hierarchical BoW model that provides a concise representation of each object class with multi-views. When the higher level BoW representation does not match with that of the query instance, further comparison can be saved. We can also incorporate similar views to reduce the storage space. We conduct experiments on a dataset of 3D object classes, and show that the proposed approach achieves higher efficiency in terms of lower computational complexity and storage space while preserving good matching performance.