Object detection, which is one of the most fundamental visual recognition tasks, has been a hotspot in computer vision. CNN (Convolutional Neural Networks) have widely employed for building detector. Due to success RPN (Region Proposal Network), two-stage detectors get both classification accuracy and precise regression bounding boxes. However, they still struggle small-size object detection. I...

The “binding problem” is discussed with reference to feature integration and visual search. Neuropsychological and neurophysiological findings support the existence of multiple visual areas within the primate cortex that respond to primary features of objects and spatial locations. Evidence from studies with hemineglect and Balint’s syndrome supports the role of spatial attention in feature int...

Visual attention affects both perception and neuronal responses. Whether the same neuronal mechanisms mediate spatial attention, which improves perception of attended locations, and nonspatial forms of attention has been a subject of considerable debate. Spatial and feature attention have similar effects on individual neurons. Because visual cortex is retinotopically organized, however, spatial...

Spatial relation terms can generally indicate spatial relations described in natural language context. Their semantic representation is closely related to geographical entities and their characteristics e.g. geometry, scale and geographical feature types. This paper proposes a quantitative approach to explore the semantic relevance of spatial relation terms and geographical feature types of geo...

Map matching of GPS trajectories from a sequence of noisy observations serves the purpose of recovering the original routes in a road network. In this work in progress, we attempt to share our experience of feature construction in a spatial database by reporting our ongoing experiment of feature extraction in Conditional Random Fields (CRFs) for map matching. Our preliminary results are obtaine...

Traditional two-step localization methods and direct have practical problems when they are used for underwater acoustic source localization. In this paper, a method based on the feature-level information fusion is proposed, in which Hough Transform exploited to detect line characteristics of spatial features target. A secondary accumulation procedure proposed extract fuse good instead fusing al...

SPATIAL ARRANGEMENT AS A PART OF GEOSPATIAL FEATURE ONTOLOGIES Jonathan R. Clark, Ph.D George Mason University, 2012 Dissertation Director: Dr. Anthony Stefanidis The geospatial sciences have always employed ontologies to describe spatial data, conduct analysis, and to design the systems and methods for conducting geospatial operations. While research on geospatial ontologies has addressed non-...

Recently, a large set of electroencephalography (EEG) data is being generated by several high-quality labs worldwide and is free to be used by all researchers in the world. On the other hand, many neuroscience researchers need these data to study different neural disorders for better diagnosis and evaluating the treatment. However, some format adaptation and pre-processing are necessary before ...

In this paper we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similaritybased objective function over transformation space given a nonparametric representation of the joint featu...