IP protection

1 Please provide a short description of the state-of-the-art and/or current trends in the field? How does the result fit into it?
The state of the art is underpinned by the clustering techniques for landmark and event detection, by travel itinerary elicitation and activity recommendations. Browsing through image collections of such magnitude is currently supported by the  use of tags. However, tags suffer from several limitations—such as polysemy, lack of uniformity, and spam—thus not presenting an adequate solution to the problem of content organization. Therefore, automated content organization methods are of particular importance to improve the content-consumption experience. Because it’s common for users to associate their photo-captured experiences with some landmarks—for example, a tourist site or an event, such as a music concert or a gathering with friends—we can view landmarks and events as natural units of organization for large image collections. It’s for this reason that automating the process of detecting such concepts in large image sets can enhance the experience of accessing massive amounts of pictorial content.
2 What is the problem/need/knowledge gap that the research result is responding to?  How was it addressed before?
The knowledge gap is described by the complexities in clustering huge data pictorial volumes with noisy and dynamic content. Extracting large-scale knowledge bases from Web data can be split into three major tasks: 1) detecting and disambiguating entities in their given context, 2) detecting binary relationships among entities (e.g., RDF-style facts), and 3) filtering and detecting inconsistencies among facts which may involve also reasoning about higher-arity relationships (e.g., when combining binary facts also with additional properties such as time annotations). Although these challenges were addressed by conventional clustering schemas with limited success, ClustTour  presents a scheme for automatically detecting landmarks and events in tagged image collections. ClustTour is based on the simple yet elegant concept of image similarity graphs as a means of combining multiple notions of similarity between images in a photo collection; in this case, ClustTour uses visual and tag similarity, performing clustering on such image similarity graphs by means of community detection, a process that identifies on the graph groups of nodes that are more densely connected to each other than to the rest of the network. In contrast to conventional clustering schemes such as k-means or hierarchical agglomerative clustering, community detection is computationally more efficient and doesn’t require the number of clusters to be provided as input. Subsequently, as landmarks or events by use of features related to the temporal, social, and tag characteristics of image clusters. In the case of landmarks, a cluster-merging step is conducted on the basis of spatial proximity to enrich our landmark model.
3 What is the potential for further research?
There is a need to research into ways to achieve applicability for real time detection of interesting monuments and events in social media content. The modern science of networks has brought significant advances to our understanding of complex systems. One of the most relevant features of graphs representing real systems is community structure, or clustering, i.e. the organization of vertices in clusters, with many edges joining vertices of the same cluster and comparatively few edges joining vertices of different clusters. Such clusters, or communities, can be considered as fairly independent compartments of a graph, playing a similar role like, e.g., the tissues or the organs in the human body. Detecting communities is of great importance in sociology, biology and computer science, disciplines where systems are often represented as graphs. This problem is very hard and not yet satisfactorily solved, despite the huge effort of a large interdisciplinary community of scientists working on it over the past few years. A thorough exposition of the topic needs to be researched, from the definition of the main elements of the problem, to the presentation of most methods developed, with a special focus on techniques designed by statistical physicists, from the discussion of crucial issues like the significance of clustering and how methods should be tested and compared against each other, to the description of applications to real networks.
4 What is the proposed method of IPR-protection? (patent, license, trademark etc.)
ClustTour is patentable because it meets specific requirements that include e.g. novelty and integration of software and hardware. Patents are handled somewhat differently in different countries and so the requirements for a patent to be granted may vary. For example, in the US, software can be quite freely patented where as in the EU, software is not patentable (though patent lawyers have found ways to get patents for software or parts of software). Digital technologies are characterized by several unusual features. The costs of reproduction are insignificant, as compared with the costs of copying physical products. For these reasons, digital technologies make it difficult to protect innovations through IPRs. Thus USPTO patent is considered to be the suitable solution to have the widest geographic coverage since the product refers to global markets.
5 What are the steps that need to be taken in order to secure the IPR-protection? What is the cost of IPR-protection?
In order to apply for USPTO patent for ClustTour the following steps must be taken:

  • Preparation of a written description of ClustTour with all necessary drawings and organizational materials
  • Preparation of prototype that will be used as a blueprint for ClustTour

The cost is 700 euros plus 350 euros maintenance fee every three years plus 1500 for file preparation.

6 What is you overall assessment of the scientific maturity of the research result?
The scientific maturity of the research result has reached a satisfactory level. Further improvements can be implemented regarding applicability of dynamic datasets, improvement of automatic titling, improvement of cluster precision and automatic categorization of clusters to fine grained classes.


Please put X as appropriate. 1 2 3 4 5
Scientific maturity X
Synergies X
State-of-the-art/innovation X
IPR-potential x

Bookmark the permalink. Follow any comments here with the RSS feed for this post. Post a comment or leave a trackback: Trackback URL.

Post a Comment

You must be logged in to post a comment.

Request a proposal

Valorisation Plan Authors

Related Documents

There in no related documents

Visit the other applications of the INTERVALUE Platform: R&D Repository | IP Agreements

© 2009-2010 INTERVALUE Project