Automatic tagging by exploring tag information capability and correlation

Automatic tagging can automatically label images and videos with semantic tags to significantly facilitate multimedia search and organization. However, most of existing tagging algorithms often don't differentiate between tags used to describe visual content, and neglect the semantic correlation of the assigned tag set. In this paper, we propose a novel automatic tagging algorithm which tags a test image or video with an Informative and Correlative Tag (ICTag) set. The assigned ICTag set can provide a more precise description of the multimedia object by exploring both the information capability of individual tags and the tag-to-set correlation. Measures to effectively estimate the information capability of individual tags and the correlation between a tag and the candidate tag set are designed. To reduce the computational complexity, we also introduce a heuristic method to achieve efficient automatic tagging. We conduct extensive experiments on the NUS-WIDE web image dataset downloaded from Flickr and the MCG-WEBV web video dataset downloaded from YouTube. The results confirm the efficiency and effectiveness of our proposed algorithm.