When applying powerful deep learning approaches on real world tasks like pixel level annotation of urban scenes it becomes clear that even those strong learners may fail dramatically and are still not ready for deployment in the wild. For semantic segmentation, one of the main practical challenges...
04b Atto di convegno in volume
-
-
In this work, we formulate Newron:a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of Newronallow the network to be interpretable without affecting their...
-
Architectures that model language and vision together havereceived much attention in recent years. Nonetheless, most tasks in this field focus on end-to-end applications without providing insights on whether it is the underlying semantics of visual objects or words that is captured. In this paper...
-
The StoryBook project stems from the cooperation between Sapienza Università di Roma, the company Aton IT and the historic publishing house L’Erma di Bretschneider. The project deals with the broad area of Digital Humanities and has favored the development of a prototype system for semi-automatic...
-
The prevalence of video content consumption prompted book publishers to adopt this medium as a way to advertise books, through so called book trailers. Beyond advertising, a book’s video presentation may provide information to potential future readers so they can make an informed choice on whether...
-
Multimedia storytelling is an effective and engaging method to convey information in multiple domains. Specifically, book trailers–video advertisements for books–positively influence the desire to learn and the motivation to read. This work describes the design and implementation of Storybook, a...
-
The widespread diffusion of Internet-of-Things (IoT) technologies is prompting organizations to rethink their business processes (BPs) towards incorporating the data collected from IoT devices directly into BP models for improved effectiveness and timely decision making. Nonetheless, IoT devices...
-
Big Data pipelines are essential for leveraging Dark Data, i.e., data collected but not used and turned into value. However, tapping their potential requires going beyond the current approaches and frameworks for managing their life-cycle. In this paper, we present the challenges associated to the...
-
Various optimization-based process synthesis approaches exist to propose a process structure and associated parameters, which have been applied on many applications. The goal of this work is to provide a comparison of methods on a common process synthesis problem. Three methods are compared on an...
-
This paper investigates various ways of minimizing energy consumption in Wireless Sensor Networks (WSNs). We are interested in those methods and technologies that allow network nodes to drastically decrease energy consumption by turning off their primary communication circuitry (main radio),...