A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Minimum explanation complexity for MOD based visual concept detection
2010
Proceedings of the international conference on Multimedia information retrieval - MIR '10
Preserved Fulltext
We propose the use of the recently introduced MOD salient points for subimage visual concept detection. ...
Visual concept detection in images has been a challenging task for many years. ...
We propose the Minimum Explanation Complexity for classifier design, that aims to search for less complex but equally effective classifiers. ...
doi:10.1145/1743384.1743479
dblp:conf/mir/OerlemansL10
fatcat:fuemoaj3ijfg7l2lzbaixstlse
Toward the effective use of educational program animations: The roles of student's engagement and topic complexity
2013
Computers & Education
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Programming is one of the most complex subjects in computer science degrees. Program visualization is one of the approaches adopted to make programming concepts more accessible to students. ...
, and there is a learning improvement for highly complex topics using the viewing approach. ...
No difference was detected for simple topics. For medium complex topics, both uses of animations delivered better results than the traditional approach. ...
doi:10.1016/j.compedu.2013.02.013
fatcat:a65jfhnkajglriim2mzj623hna
Critical Analysis of Steganography "An Art of Hidden Writing"
2016
International Journal of Security and Its Applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Critical analysis is based on the type of cover object used, domain of the algorithm and important properties that are used as evaluative measures for steganographic system. Cover Object: It is the input ...
Cover Medium Used for Steganography Different digital medium are used as cover medium for hiding the data. On the basis of medium, steganography is named accordingly. ...
Nadeem Salamat, Associate Professor at the Department of Basic Sciences, Khwaja Freed Information Technology University, R.Y.Khan, Pakistan, for help. ...
doi:10.14257/ijsia.2016.10.3.24
fatcat:qz6crhbhgzegrb36pyjzc26ynq
VAE-CE: Visual Contrastive Explanation using Disentangled VAEs
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper we propose a model, denoted as Variational Autoencoder-based Contrastive Explanation (VAE-CE), that represents data with high-level concepts and uses this representation for both classification ...
Often a rich set of meaningful concepts exist in the domain that can much more precisely describe each datapoint. Such concepts can also be highly useful for interpreting the model's classifications. ...
Concepts can also be an
uating explanations, resting on access to the true generat- integral part of a model, e.g. by first detecting concepts and
ing process of the data. ...
arXiv:2108.09159v1
fatcat:onejltviqzavfm6phethxxux3q
Prototypical implementation of location-aware services based on a middleware architecture for super-distributed RFID tag infrastructures
2006
Personal and Ubiquitous Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
We provide evidence of the feasibility and effectiveness of a middleware architecture for mobile devices which employs dense distributions of small computerized entities for providing fault-tolerant location-aware ...
We do so by describing exemplary implementations based on radio frequency identification (RFID) as an enabling technology. ...
We further wish to acknowledge Nicola Oprecht for his work on the implementation of the SDRI Tracking and Positioning prototype [15] , and Marco Bär for his work on the Collaborative SDRI Mapping system ...
doi:10.1007/s00779-006-0107-2
fatcat:spm4mweawjev3nxettnrsfofta
A responsive MRI contrast agent to monitor functional cell status
2006
NeuroImage
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The DTPA-based, insoluble, inactive contrast agent was internalized into dendritic cells by phagocytosis. ...
Detectability limits in the T 1 -weighted MR images were estimated in phantoms and in vivo in the rat brain. ...
Acknowledgments We gratefully acknowledge the financial support by the European Commission for an International Re-integration grant to UH ( ...
doi:10.1016/j.neuroimage.2006.05.009
pmid:16815042
fatcat:xcnvm7klpvbtnoebfgz65a5fqa
Tensor decompositions and data fusion in epileptic electroencephalography and functional magnetic resonance imaging data
2016
Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Despite the well-developed theoretical framework, tensor-based analysis of real, large-scale clinical datasets is still scarce. Indeed, the application of tensor methods is not straightforward. ...
The aim of this paper is to provide a general guideline for these choices and illustrate them through successful applications in epilepsy. ...
ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers for their valuable suggestions. ...
doi:10.1002/widm.1197
fatcat:fr4mjfg5gffpvasjbc6hozyxse
The gesturer is the speaker
2013
2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We provide evidence in support of the hy pothesis from gesture literature and audio-visual synchrony studies. ...
However, because model complexity is neutral to the-gesturer-is-the-speaker concept, we will concentrate our efforts on a simple method that detects and tracks gestures of people in conference meeting ...
METHODOLOGY In order to perform speaker diarization based on the hypoth esis: the gesturer is the sp eaker, we need to design mod ules to determine: a) the number of speakers b) their loca tion and c) ...
doi:10.1109/icassp.2013.6638359
dblp:conf/icassp/GebreWH13
fatcat:jrzm3jlqeferrok434co3h4kfa
Detection of Plagiarism in Arabic Documents
2012
International Journal of Information Technology and Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Many language-sensitive tools for detecting plagiarism in natural language documents have been developed, particularly for English. ...
Detecting plagiarism in Arabic documents is particularly a challenging task because of the complex linguistic structure of Arabic. ...
In APlag, we choose to use LCS, because it is based on the concept of similarity rather than distance. ...
doi:10.5815/ijitcs.2012.10.10
fatcat:uc3sxp3ctrgvfemkcw3tx7dagy
Vajra
2019
Proceedings of the 24th International Conference on Intelligent User Interfaces - IUI '19
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The proposed semantic parsing model aims to reduce the barriers for producing well-formed code (syntactic gap) and for exploring thirdparty APIs (lexico-semantic gap). ...
We present a novel end-user programming paradigm for Python, which maps natural language commands into Python code. ...
ACKNOWLEDGMENTS We express our gratitude to the anonymous reviewers for their valuable feedback as well as the members of AI Systems Lab Manchester for many insightful discussions. ...
doi:10.1145/3301275.3302267
dblp:conf/iui/SchlegelLHF19
fatcat:iiaxo57pdfaj7cqlhidzinxi7q
An introduction to ACAS Xu and the challenges ahead
2016
2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
As work on Minimum Operational Performance Standards (MOPS) for ACAS Xu just started, it is of interest to know which parts of the MOPS are already decided, which remain flexible for the industries to ...
It is followed by a presentation of concepts specific to ACAS Xu such as the tailored threat logic, horizontal CA logic, CA coordination and automatic responses. ...
The authors would like to thank Christian Aveneau for sharing his extended expertise on the matter, as well as Catherine Ronflé-Nadaud and Julien Farjon for the enlightening discussions. ...
doi:10.1109/dasc.2016.7778055
fatcat:vgfcssxwdzgrlpq6gs4byyzxq4
Explainable Artificial Intelligence: What Do You Need to Know?
[chapter]
2020
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We demonstrate that a 'one-size-fits-all' explanation is insufficient to capture the complexity of needs. ...
In domains which require high risk and high consequence decision making, such as defence and security, there is a clear requirement for artificial intelligence (AI) systems to be able to explain their ...
In summary, explanation needs in the real world are complex and context dependent. ...
doi:10.1007/978-3-030-50353-6_20
fatcat:32ywvkrtljfoxbtgjdiqb5ueoi
Local pulmonary structure classification for computer-aided nodule detection
2006
Medical Imaging 2006: Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
solutions are available in literature, and which is better suited for visualization. ...
Recently a number of techniques have been proposed for automated detection and classification of nodules in thin-slice CT including: region growing and automatic threshold determination, 2 template matching ...
The authors like to thank Imad Zoghlami and Visvanathan Ramesh from Siemens Corporate Research for very helpful discussions. ...
doi:10.1117/12.654060
dblp:conf/miip/BahlmannLO06
fatcat:kegoceob4ven5h2vinu2gqlppm
EDITORS'INTRODUCTION
1985
Journal of Regional Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Though Allmendinger (2002) mentions complexity theory as a new concept influencing planning science, he does not seem to comprehend its full importance for the planning realm and the extent to which complexity ...
In sum, models try to visualize and explore invisible worlds. ...
Real-time visualization makes it practical to study visual experience and time-based analysis in virtual environments. ...
doi:10.1111/j.1467-9787.1985.tb00319.x
fatcat:37mvzve32ne33mkhsft2ybiu64
Detecting behavior types of moving object trajectories
2018
International Journal of Data Science and Analytics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In order to detect behaviors, we propose an algorithm that analyses the evolution of the discovered formal concepts over time. ...
Refined or coarse analysis can thus be performed for a given situation. ...
Acknowledgments The authors would like to thank the anonymous reviewers for comments and suggestions on earlier drafts of this paper. ...
doi:10.1007/s41060-017-0076-8
dblp:journals/ijdsa/AlMuhisenDQ18
fatcat:hpg352ltorekjbfmygtq2q25t4
« Previous
Showing results 1 — 15 out of 7,571 results