With advances in machine vision systems (e.g., artificial eye, unmanned aerial vehicles, surveillance monitoring) scene semantic recognition (SSR) technology has attracted much attention due to its related applications such as autonomous driving, tourist navigation, intelligent traffic and remote sensing. Although tremendous progress been made visual interpretation, several challenges remain (i...

We address semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling. Tracklet characterizes varying spatial-temporal relations of video object which, however, quite often suffers from sporadic local outliers. In order to acquire highquality tracklets, we propose a transductive infer...

The method presented in this paper aims to reduce the computational costs of some kinds of navigation in a world with obstacles. We give algorithms to capture the logical structure of an object given a polygonal representation of it. Then these algorithms are used in conjunction with the notion of functional granularity to handle navigation of a moving object. 1 Framework The class of problems ...

Perceiving not just values, but relations between values, is critical to human cognition. We tested the predictions of a proposed mechanism for processing categorical spatial relations between two objects-the shift account of relation processing-which states that relations such as 'above' or 'below' are extracted by shifting visual attention upward or downward in space. If so, then shifts of at...

Management of changes during software development is a central problem in software object management. Successful propagation of changes requires effective use of relationships among objects. The structure of relationships identifies the direction, order, and extent of change propagation, while the semantics of relationships indicate the kinds of changes to be made. Many data models proposed for...

Object categorization is a hot issue of an image mining. Contextual information between objects is one of the important semantic knowledge of an image. However, the previous researches for an object categorization have not made full use of the contextual information, especially the spatial relations between objects. In addition, the object categorization methods, which generally use the probabi...

This paper investigates a new data model for the realization of a three-dimensional (3D) moving object database system. In contrast to the traditional approach, it can deal with spatio-temporal characteristics of moving objects in the 3D space. A spatio-temporal sampling theory is introduced that enables a database system to store and manipulate all of the necessary spatio-temporal information ...

ion of Implicit Domain Concepts The fact that EUREKA indexes the enhanced problem representation means that its expert-level schemas are not limited to the problem’s initial descriptors. Instead, physics concepts and other inferences about object relations and features are eligible to become norms and indices. This is important for abstracting useful domain-specific concepts that are defined as...