Search results for "artificial intelligence"
showing 10 items of 6122 documents
Color Correction for Image Stitching by Monotone Cubic Spline Interpolation
2015
This paper proposes a novel color correction scheme for image stitching where the color map transfer is modelled by a monotone Hermite cubic spline and smoothly propagated into the target image. A three-segments monotone cubic spline minimizing color distribution statistics and gradient differences with respect to both the source and target images is used. While the spline model can handle non-linear color maps, the minimization over the gradient differences limits strong alterations on the image structure. Adaptive heuristics are introduced to reduce the minimization search space and thus computational time. Experimental comparisons with respect to the state-of-the-art linear mapping model…
3D skeleton-based human action classification: A survey
2016
In recent years, there has been a proliferation of works on human action classification from depth sequences. These works generally present methods and/or feature representations for the classification of actions from sequences of 3D locations of human body joints and/or other sources of data, such as depth maps and RGB videos.This survey highlights motivations and challenges of this very recent research area by presenting technologies and approaches for 3D skeleton-based action classification. The work focuses on aspects such as data pre-processing, publicly available benchmarks and commonly used accuracy measurements. Furthermore, this survey introduces a categorization of the most recent…
An A* Based Semantic Tokenizer for Increasing the Performance of Semantic Applications
2013
Semantic Applications (SAs) makes use of ontolo- gies and their performance can depend on the syntactic labels of the modeled entities; even if several approaches have been devised to formalize ontologies, no formal approaches have been devised for naming their constituents, which look as long word concatenations without any particular separation. We present a novel semantic tokenizer that finds the sub-words through an application of the A* based search algorithm; the A* functions rely on a set of linguistic criteria and on the meta-cognitive perspective of the activity of reading.
An on-line learning method for face association in personal photo collection
2012
Due to the widespread use of cameras, it is very common to collect thousands of personal photos. A proper organization is needed to make the collection usable and to enable an easy photo retrieval. In this paper, we present a method to organize personal photo collections based on ''who'' is in the picture. Our method consists in detecting the faces in the photo sequence and arranging them in groups corresponding to the probable identities. This problem can be conveniently modeled as a multi-target visual tracking where a set of on-line trained classifiers is used to represent the identity models. In contrast to other works where clustering methods are used, our method relies on a probabilis…
An Innovative Statistical Tool for Automatic OWL-ERD Alignment
2016
Aligning two representations of the same domain with different expressiveness is a crucial topic in nowadays semantic web and big data research. OWL ontologies and Entity Relation Diagrams are the most widespread representations whose alignment allows for semantic data access via ontology interface, and ontology storing techniques. The term ""alignment" encompasses three different processes: OWL-to-ERD and ERD-to-OWL transformation, and OWL-ERD mapping. In this paper an innovative statistical tool is presented to accomplish all the three aspects of the alignment. The main idea relies on the use of a HMM to estimate the most likely ERD sentence that is stated in a suitable grammar, and corre…
Keyword Based Keyframe Extraction in Online Video Collections
2015
Keyframe extraction methods aim to find in a video sequence the most significant frames, according to specific criteria. In this paper we propose a new method to search, in a video database, for frames that are related to a given keyword, and to extract the best ones, according to a proposed quality factor. We first exploit a speech to text algorithm to extract automatic captions from all the video in a specific domain database. Then we select only those sequences (clips), whose captions include a given keyword, thus discarding a lot of information that is useless for our purposes. Each retrieved clip is then divided into shots, using a video segmentation method, that is based on the SURF d…
PDA -- Remote Display Interaction Framework
2008
This paper discusses the design of a PDA-driven remote display control system which was designed for a pervasive computing scenario. Our solution enables a PDA to perform as an interaction device (such as keyboard or mouse) to operate applications which are using remote displays. Our system consists of two components: one devoted to pair users and remote display according to their relative position, and one to provide the PDA with appropriate graphical interfaces and ad-hoc communication protocols. Besides a case study on the use of remote displays during a course with in our department, this paper discusses system highlights, components, and experiments as for standard multimedia and offic…
A Modular Architecture for Adaptive ChatBots
2011
We illustrate an architecture for a conversational agent based on a modular knowledge representation. This solution provides intelligent conversational agents with a dynamic and flexible behavior. The modularity of the architecture allows a concurrent and synergic use of different techniques, making it possible to use the most adequate methodology for the management of a specific characteristic of the domain, of the dialogue, or of the user behavior. We show the implementation of a proof-of-concept prototype: a set of modules exploiting different knowledge representation techniques and capable to differently manage conversation features has been developed. Each module is automatically trigg…
Three-dimensional matching based resource provisioning for the design of low-latency heterogeneous IoT networks
2019
Internet-of-Things (IoT) is a networking architecture where promising, intelligent services are designed via leveraging information from multiple heterogeneous sources of data within the network. However, the availability of such information in a timely manner requires processing and communication of raw data collected from these sources. Therefore, the economic feasibility of IoT-enabled networks relies on the efficient allocation of both computational and communication resources within the network. Since fog computing and 5G cellular networks approach this problem independently, there is a need for joint resource-provisioning of both communication and computational resources in the networ…
Chatbots as Interface to Ontologies
2014
Chatbots are simple conversational agents using 'pattern matching rules' to carry out the dialogue with the user and various expedients to improve their credibility. However, the rules on which they are based on are too restrictive and their language understanding capability is very limited. Nevertheless chatbots are widespread in several applications, especially to provide information to users in a new and enjoyable way. In this chapter we describe different chatbot architectures, exploiting the use of ontologies in order to create clever information suppliers overcoming the main limits of chatbots: The knowledge base building and the rigidness of the dialogue mechanism. © Springer Interna…