Automatic Image Annotation via Label Transfer in the Semantic Space
This addresses the problem of searching and browsing large-scale image collections for computer vision and pattern recognition, but it is incremental as it builds on existing label transfer methods.
The paper tackles automatic image annotation by proposing a label propagation framework using Kernel Canonical Correlation Analysis (KCCA) to create a semantic space that preserves visual-textual correlations, showing it can be applied to state-of-the-art label transfer methods for significant improvements and works with both expert-annotated and noisy user-generated tags.
Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images.