No abstract

No abstract

No abstract

Abstract-This paper addresses learning based characterization of fine art painting styles. The research has the potential to provide a powerful tool to art historians for studying connections among artists or periods in the history of art. Depending on specific applications, paintings can be categorized in different ways. In this paper, we focus on comparing the painting styles of artists. To profile the style of an artist, a mixture of stochastic models is estimated using training images.

This study focuses on the impact of knowledge creation capability and absorptive capacity on product innovativeness. Capabilities contribute through their uniqueness, their integration into effective configurations, and their deployment in response to external environment changes. Therefore, this study examines the individual (uniqueness) and interactive (integration) effects of knowledge creation capability and absorptive capacity on product innovativeness as well as how these effects vary in differing technologically turbulent contexts (deployment). Based on a survey of 212 Chinese firms, this study finds that in addition to their individually positive effects, knowledge creation capability and absorptive capacity have a synergistic effect on product innovativeness. Moreover, the individual effect of knowledge creation capability and the synergistic effect become stronger as technological turbulence increases, whereas the impact of absorptive capacity tends to be dampened by technological turbulence.

In this paper, we present a probabilistic multi-task learning approach for visual saliency estimation in video. In our approach, the problem of visual saliency estimation is modeled by simultaneously considering the stimulusdriven and task-related factors in a probabilistic framework. In this framework, a stimulus-driven component simulates the low-level processes in human vision system using multiscale wavelet decomposition and unbiased feature competition; while a task-related component simulates the highlevel processes to bias the competition of the input features. Different from existing approaches, we propose a multitask learning algorithm to learn the task-related "stimulussaliency" mapping functions for each scene. The algorithm also learns various fusion strategies, which are used to integrate the stimulus-driven and task-related components to obtain the visual saliency. Extensive experiments were carried out on two public eye-fixation datasets and one regional saliency dataset. Experimental results show that our approach outperforms eight state-of-the-art approaches remarkably.

Despite of the large number of algorithms developed for clustering, the study on comparing clustering results is limited. In this paper, we propose a measure for comparing clustering results to tackle two issues insufficiently addressed or even overlooked by existing methods: (a) taking into account the distance between cluster representatives when assessing the similarity of clustering results; (b) constructing a unified framework for defining a distance based on either hard or soft clustering and ensuring the triangle inequality under the definition. Our measure is derived from a complete and globally optimal matching between clusters in two clustering results. It is shown that the distance is an instance of the Mallows distance-a metric between probability distributions in statistics. As a result, the defined distance inherits desirable properties from the Mallows distance. Experiments show that our clustering distance measure successfully handles cases difficult for other measures.

No abstract