In a visual surveillance application where a network of cameras is used to observe many people, there are numerous situations where the consistent identification of a person is an important component in the system. There are many approaches to describing the appearance of a person. In this paper, we examine a combination of two identity descriptors: standard MPEG-7 color descriptors, and spatia...

It has been proved that large-scale realistic Knowledge Based Machine Translation (KBMT) applications require acquisition of huge knowledge about language and about the world. This knowledge is encoded in computational grammars, lexicons and domain models. Another approach – which avoids the need for collecting and analyzing massive knowledge-is the Example Based approach, which is the topic of...

This paper describes a novel music playback interface, called Musicream, which lets a user unexpectedly come across various musical pieces similar to those liked by the user. With most previous “query-by-example” interfaces used for similarity-based searching, for the same query and music collection a user will always receive the same list of musical pieces ranked by their similarity and opport...

Much previous research on multiword expressions (MWEs) has focused on the tokenand typelevel tasks of MWE identification and extraction, respectively. Such studies typically target known prevalent MWE types in a given language. This paper describes the first attempt to learn the MWE inventory of a “surprise” language for which we have no explicit prior knowledge of MWE patterns, certainly no an...

This paper describes Musicream, a novel music-listening interface that lets a user unexpectedly come across various musical pieces similar to those liked by the user. Most existing “query-by-example” interfaces are based on similaritybased searching, so they return the same results for the same query, meaning that a user of those systems always receives the same list of musical pieces sorted by...

In this article, a heuristic version of Multidimensional Scaling (MDS) named , like MDS, maps objects into an Euclidean space, such that similarities are preserved. In addition of being more efficient than MDS it allows query-by-example type of query, which makes it suitable for a content-based retrieval purposes.

Multiword expressions (MWEs) are quite frequent in languages such as English, but their diversity, the scarcity of individual MWE types, and contextual ambiguity have presented obstacles to corpus-based studies and NLP systems addressing them as a class. Here we advocate for a comprehensive annotation approach: proceeding sentence by sentence, our annotators manually group tokens into MWEs acco...

In this paper we present a method for the end-user specification of consistency rules for Web documents. Temporal description logic is used as the internal formalism. It is difficult for an author of a Web document to understand and use a formal logic. Therefore the goal is to develop an intuitive front-end allowing the authors of a document to specify their requirements and constraints at an a...