The Future of Research Communications and e-Scholarship

Flickr Distance: A Relationship Measure for Visual Concepts.

Authors: Wu, Lei

Hua, Xian-Sheng

Yu, Nenghai

Ma, Wei-Ying

Li, Shipeng

This paper proposes the Flickr Distance (FD) to measure the visual correlation between concepts. For each concept, a collection of related images are obtained from the Flickr website. We assume that each concept consists of several states, e.g. different views, different semantics, etc., which are considered as latent topics. Then a latent topic visual language model (LTVLM) is built to capture these states. The Flickr distance between two concepts is defined as the Jensen-Shannon (JS) divergence between their LTVLM. Different from traditional conceptual distance measurements, which are based on Web textual documents, FD is based on the visual information. Comparing with the WordNet distance, FD can easily scale up with the increasing size of conceptual corpus. Comparing with the Google Distance (NGD) and Tag Concurrence Distance (TCD), FD uses the visual information and can properly measure the conceptual relations. We apply FD to multimedia related tasks and find methods based on FD significantly outperform those based on NGD and TCD. With the FD measurement, we also construct a large-scale visual conceptual network (VCNet) to store the knowledge of conceptual relationship. Experiments show that FD is more coherent to human cognition and it also outperforms text based distances in real-world applications.

Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence 2011

PMID: 21987557

PMCID: 0

ISSN: 1939-3539

Archive: https://archive.force11.net/node/6354

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Articles

Membership

Join the FORCE11 community and take part in our groups, conference, summer school, post on FORCE11, and attend other events.

Membership

FORCE2022 Sponsors

The FORCE11 community thanks the following organizations for their financial support of the
FORCE2022 annual conference.