Historically, figure-ground segmentation has been seen as an important and even necessary precursor for object recognition. In that context, segmentation is mostly defined as a data driven, that is bottom-up, process. As for humans object recognition and segmentation are heavily intertwined processes, it has been argued that top-down knowledge from object recognition can and should be used for ...

We identify four orthogonal dimensions along which information in engineering design organizations can be ordered, namely (i) the principle of ordering (top down vs. bottom up), (ii) the structure of ordering (aggregation-decomposition vs. generalization-specialization), (iii) the breadth of ordering (diversity vs. parsimony) and (iv) the perspective of ordering (horizontal vs. historical). Fou...

Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or language modelling text. Early systems focused on identifying isolated recurring terms in a corpus, while more recent full-coverage systems attempt to completely segment and cluster the audio into word-like units—effectively performing unsu...

two physicians, both grown up in west europe, educated also in this area (supplemented by many visits of the united states), travelled 20 years ago to japan for scientific reasons and they changed thereafter in their mental sight of the world. in a first part, the neurophysiologic basis of sensation from the sensory receptor up to the cerebral cortex (“bottom up”), the mechanisms of building me...

A unique vertical bar among horizontal bars is salient and pops out perceptually. Physiological data have suggested that mechanisms in the primary visual cortex (V1) contribute to the high saliency of such a unique basic feature, but indicated little regarding whether V1 plays an essential or peripheral role in input-driven or bottom-up saliency. Meanwhile, a biologically based V1 model has sug...

OF THE DISSERTATION Graphical Models for Object Segmentation by Rui Huang Dissertation Director: Professor Dimitris N. Metaxas Object segmentation, a fundamental problem in computer vision, remains a challenging task after decades of research efforts. This task is made difficult by the intrinsic variability of the object’s shape, appearance, and its surrounding. It is compounded by the uncertai...

Top-down instance segmentation framework has shown its superiority in object detection compared to the bottom-up framework. While it is efficient addressing over-segmentation, top-down suffers from over-crop problem. However, a complete mask crucial for biological image analysis as delivers important morphological properties such shapes and volumes. In this paper, we propose region proposal rec...

While plant diversity is well known to increase primary productivity, whether these bottom-up effects are enhanced by reciprocal top-down effects from the third trophic level is unknown. We studied whether pine tree species diversity, aphid-tending ants and their interaction determined plant performance and arthropod community structure. Plant diversity had a positive effect on aphids, but only...