Multi-view Manifold Learning for Media Interestingness Prediction

Media interestingness prediction plays an important role in many real-world applications and attracts much research attention recently. In this paper, we aim to investigate this problem from the perspective of supervised feature extraction. Specifically, we design a novel algorithm dubbed Multi-view Manifold Learning ((ML)-L-2) to uncover the latent factors that are capable of distinguishing interesting media data from non-interesting ones. By modelling both geometry preserving criterion and discrimination maximization criterion in a unified framework, (ML)-L-2 learns a common subspace for data from multiple views. The analytical solution of (ML)-L-2 is obtained by solving a generalized eigen-decomposition problem. Experiments on the Predicting Media Interestingness Dataset validate the effectiveness of the proposed method.