Date: Wednesday, May 14th, 2014
Place: Informatics Teaching Lab (ITL) — Top floor seminar room
Speaker: Yanwei Fu
Title: Relative Attribute Prediction by Robust Learning to Rank
The problem of predicting the relative attributes (e.g. image or video interestingness
from their low-level feature representations has received increasing inter-
est. As a highly subjective visual attribute, annotating the interesting-
ness 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 for-
mulating the relative attributes (e.g. 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.
Yanwei Fu is a 3rd year PhD student in our group.