In recent years there have been multiple successful attempts tackling document processing problems separately by designing task specific hand-tuned strategies. We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical series. In this paper, we address multiple tasks simultaneously such as page extraction, baseline extraction, layout analysis or multiple typologies of illustrations and photograph extraction.We propose an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks. We show that a single CNN-architecture can be used across tasks with competitive results. Moreover most of the task-specific post-precessing steps can be decomposed in a small number of simple and standard reusable operations, adding to the flexibility of our approach.

This work critically assesses the history and current state of social media scholarship in sport management research. Methodologically, the study is based on a comprehensive census review of the current body of literature in the area of social media. The review identifies 123 social media articles in sport management research that were mined from a cross-disciplinary examination of 29 scholarly journals from January 2008 (earliest found) to June 2014. The work identifies the topic areas, the platforms, the theories, and the research methods that have received the (most/least) attention of the social media research community, and provides suggestions for future research.

This study aims to obtain an in-depth understanding of the use, opportunities, and challenges related to social media (SM) in achieving relationship marketing (RM) goals in professional sport. Semistructured interviews were conducted with 26 managers of professional sport teams from the four major leagues in North America. Results outline the platforms adopted, the six intended objectives of SM use, the seven opportunities SM provides, and the seven challenges of SM as a RM medium. Theoretical and practical implications as well as suggestions for future research are provided.

Abstract. This paper examines how far state-of-the-art machine vision algorithms can be used to retrieve common visual patterns shared by series of paintings. The research of such visual patterns, central to Art History Research, is challenging because of the diversity of similarity criteria that could relevantly demonstrate genealogical links. We design a methodology and a tool to annotate efficiently clusters of similar paintings and test various algorithms in a retrieval task. We show that pretrained convolutional neural network can perform better for this task than other machine vision methods aimed at photograph analysis. We also show that retrieval performance can be significantly improved by fine-tuning a network specifically for this task.

No abstract