Interestingness Prediction by Robust Learning to Rank^*

Yanwei Fu¹, Timothy M. Hospedales¹, Tao Xiang¹, Shaogang Gong¹, and Yuan Yao²

¹School of EECS, Queen Mary University of London, UK
y.fu@qmul.ac.uk
t.hospedales@qmul.ac.uk
t.xiang@qmul.ac.uk
s.gong@qmul.ac.uk

²School of Mathematical Sciences, Peking University, China
yuany@math.pku.edu.cn

Abstract. The problem of predicting image or video interestingness from their low-level feature representations has received increasing interest. As a highly subjective visual attribute, annotating the interestingness value of training data for learning a prediction model is challenging. To make the annotation less subjective and more reliable, recent studies employ crowdsourcing tools to collect pairwise comparisons – relying on majority voting to prune the annotation outliers/errors. In this paper, we propose a more principled way to identify annotation outliers by formulating the interestingness prediction task as a unified robust learning to rank problem, tackling both the outlier detection and interestingness prediction tasks jointly. Extensive experiments on both image and video interestingness benchmark datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives.

^*The research of Yuan Yao was supported in part by National Basic Research Program of China (973 Program 2012CB825501), NSFC grant 61071157, and a joint NSFC-Royal Society grant 61211130360, IE110976 with Tao Xiang.

LNCS 8690, p. 488 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer International Publishing Switzerland 2014