A fast solution for automatic image annotation based on multi-modal graph

In order to improve the computing speed of automatic image annotation. We propose a fast solution for this problem in this paper. First, the proposed approach describes the relationship between the low-level features, annotated words and image by a multi-modal graph which is linear correlation, block-wise and community-like structure. Second, we, to achieve fast solution of the problem, exploit the linearity by using low-rank matrix approximation, and the community structure by graph partitioning, followed by the Sherman-Morrison lemma for matrix inversion. Experimental results on the Corel image datasets show the effectiveness of the proposed approach in terms of processing time performance.