UC Riverside

Describing visual image contents by semantic concepts is an effective and straightforward way to facilitate various high level applications. Inferring semantic concepts from low-level pictorial feature analysis is challenging due to the semantic gap problem, while manually labeling concepts is unwise because of a large number of images in both online and offline collections. In this paper, we present a novel approach to automatically generate intermediate image descriptors by exploiting concept co-occurrence patterns in the pre-labeled training set that renders it possible to depict complex scene images semantically. Our work is motivated by the fact that multiple concepts that frequently co-occur across images form patterns which could provide contextual cues for individual concept inference. We discover the co-occurrence patterns as hierarchical communities by graph modularity maximization in a network with nodes and edges representing concepts and co-occurrence relationships separately. A random walk process working on the inferred concept probabilities with the discovered co-occurrence patterns is applied to acquire the refined high level image semantic representation. Through experiments in applications including automatic image annotation, semantic image retrieval, moth species identification and multi-pedestrian tracking on several challenging datasets, we demonstrate the effectiveness of the proposed concept co-occurrence patterns as well as the proposed image semantic representation in comparison with state-of-the-art approaches.