University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Images as Sets of Locally Weighted Features

Images as Sets of Locally Weighted Features

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

Abstract: I`ll present a novel image representation in which images are modeled as order-less sets of weighted visual features. Each visual feature is associated with a weight factor that may inform its relevance. This framework can be applied to various bag-of-patches approaches such as the bag-of-visual-word or the Fisher kernel representations. We suggest that if dense sampling is used, different schemes to weight local features can be evaluated, leading to results that are often better than the combination of multiple sampling schemes, at a much lower computational cost, because the features are extracted only once. This allows our framework to be a testbed for saliency estimation methods in image categorization tasks. We explored two main possibilities for the estimation of local feature relevance. The first one is based on the use of saliency maps obtained from human feedback, either by gaze tracking or by mouse clicks. The method is able to profit from such maps, leading to a significant improvement in categorization performance. The second possibility is based on automatic saliency estimation methods, including Itti&Koch`s method and the SIFT `s DoG. We evaluated the proposed framework and saliency estimation methods using an in house dataset and the PASCAL VOC 2008 /2007 dataset, showing that some of the saliency estimation methods lead to a significant performance in comparison to the standard unweighted representation.

This talk is part of the Microsoft Research Cambridge, public talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity