We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face images, without any explicit part supervision. The observation motivates a new method for finding faces through scoring facial parts responses by their spatial s...

We report on the large-scale acquisition of class attributes with and without the use of lists of representative instances, as well as the discovery of unary attributes, such as typically expressed in English through prenominal adjectival modification. Our method employs a system based on compositional language processing, as applied to the British National Corpus. Experimental results suggest ...

Previous experiments investigating ERP correlates of anticipatory attention shifts triggered by central symbolic cues have identified a contralateral "early directing attention negativity," which was assumed to be generated by processes involved in the control of spatial orienting. Here we demonstrate that this component is not directly linked to the control of attentional shifts, but instead r...

We present an interactive graphical approach for the explicit specification of semantics for volume visualization. This explicit and graphical specification of semantics for volumetric features allows us to visually assign meaning to both input and output parameters of the visualization mapping. This is in contrast to the implicit way of specifying semantics using transfer functions. In particu...

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to map into compressed binary representation independent sensitive attributes. show in an information bottleneck framework, parsimonious should filter out related attributes if they are provided directly decoder. Empirical results method achieves state-o...

Personalized ranking is a typical task of recommender systems. It can provide a set of items for specific user and help recommender systems more correctly direct each item to its user. Recently, as the dramatically increasing social media, an entity, i.e., user and item, usually associates with multiple kinds of characterized information, e.g., explicit ratings, implicit feedbacks, and multi-ty...

We propose a new method for assessing agents influence in network structures, which takes into consideration nodes attributes, individual and group influences of nodes, and the intensity of interactions. This approach helps us to identify both explicit and hidden central elements which cannot be detected by classical centrality measures or other indices.

UML contains a variety of diagram types for modeling objectoriented systems at various levels of abstraction. This paper describes how the comprehensibility of object models can be increased by augmenting UML diagrams with additional information about the behavior of attributes. A recent notion of “roles of variables” is used as the notation for describing the behavior. The increased comprehens...

This paper aims to provide grounding for the development of social intelligence in autonomous mobile robots by highlighting that little has been done in developing an explicit social framework for a team of robots engaged in collaborative work. Only recently has work been undertaken on developing social attributes and functionality in robotics [23] [16]. This review provides a somewhat historic...