Weakly-supervised temporal action localization aims to learn detecting intervals of classes with only video-level labels. To this end, it is crucial separate frames from the background (i.e., not belonging any classes). In paper, we present a new perspective on where they are modeled as out-of-distribution samples regarding their inconsistency. Then, can be detected by estimating probability ea...

The use of ontologies enables semantically enriched access to a variety of digital resources. Historical domains impose a number of challenges to creating ontologies, e.g. modeling temporal relations, handling subjectivity, and dealing with vagueness. This research develops a case study in the History of Science that illustrates how to conceptualise and reason about a historical domain, and sug...

This paper introduces a new acoustic modeling method called Gaussian Dynamic Warping (GDW). It is targeting real world applications such as voice-based entrance door security systems, the example presented in this paper. The proposed approach uses a hierarchical statistical framework with three levels of specialization for the acoustic modeling. The highest level of specialization is in additio...

residential location choice modeling is one of the areas in transportation planning that attempts to examine households location search behavior incorporating their trade-offs between housing quality, prices or rents, distance to work and other key factors. this brings up the need to come up with methods to logically allocate credible choice alternatives for individuals.this article attempts to...

Improved support for modeling information systems involving time-varying, georeferenced information, termed spatio-temporal information, has been a longterm user requirement in a variety of areas, such as cadastral systems that capture the histories of landparcels, routing systems computing possible routes of vehicles, and weather forecasting systems. This chapter concerns the conceptual databa...