Filters








66 Hits in 5.8 sec

Skew-sensitive boolean combination for adaptive ensembles – An application to face recognition in video surveillance

Paulo V.W. Radtke, Eric Granger, Robert Sabourin, Dmitry O. Gorodnichy
2014 Information Fusion  
For instance, in video surveillance applications, face recognition (FR) is employed to detect the presence of target individuals of interest in potentially complex and changing environments.  ...  Given a diversified pool of classifiers and a desired false positive rate (fpr), the new Skew-Sensitive Boolean Combination (SSBC) technique exploits the Precision-Recall Operating Characteristic (PROC  ...  Adaptive skew-sensitive boolean combination In this section, an adaptive Skew-Sensitive Boolean Combination (SSBC) technique is proposed for the selection and fusion of the most accurate ensembles according  ... 
doi:10.1016/j.inffus.2013.11.001 fatcat:jmhtto5utrfcxmlwu6kqxsndje

Adaptive skew-sensitive fusion of ensembles and their application to face re-identification

Miguel De-la-Torre, Eric Granger, Robert Sabourin
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
Adaptive classifier ensembles have been shown to improve the accuracy and robustness of systems for face recognition (FR) in video surveillance.  ...  In this paper, a skew-sensitive ensemble is proposed to adaptively combine classifiers trained with data selected to have varying levels of imbalance and complexity.  ...  ADAPTIVE SKEW-SENSITIVE ENSEMBLES FOR VIDEO-TO-VIDEO FACE RECOGNITION Figure 1 depicts the proposed architecture for an adaptive skew-sensitive multi-classifier system (MCS) for video-tovideo FR.  ... 
doi:10.1109/ijcnn.2015.7280433 dblp:conf/ijcnn/De-la-TorreGS15 fatcat:zygwirlnrjcydl2rks6ymve25m

Adaptive Ensemble Selection for Face Re-identification under Class Imbalance [chapter]

Paulo Radtke, Eric Granger, Robert Sabourin, Dmitry Gorodnichy
2013 Lecture Notes in Computer Science  
Given a diversified pool of base classifiers and a desired false positive rate (f pr), the Skew-Sensitive Boolean Combination (SSBC) technique allows to adapt the selection of ensembles based on changes  ...  Using face tracking, a high level of discrimination between target and non-target individuals may be achieved by accumulating SSBC predictions for faces captured corresponding to a same track in video  ...  Face Recognition in Video Surveillance The problem addressed in this paper is the design of accurate and robust systems for video-to-video FR from footage recorded across a network of surveillance cameras  ... 
doi:10.1007/978-3-642-38067-9_9 fatcat:qsizej6nd5b27kh2odioc6zlxy

A comparison of adaptive matchers for screening of faces in video surveillance

Miguel De-la-Torre, Paulo V. W. Radtke, Eric Granger, Robert Sabourin, Dmitry O. Gorodnichy
2012 2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications  
An experimental methodology is proposed to assess their performance for video surveillance applications.  ...  Video-based face screening is essentially a detection problem where faces captured in video sequences are matched against the facial models of individuals of interest.  ...  This work was also supported by the Programa de Mejoramiento del Profesorado of the Secretaría de Educación Pública in México (PROMEP/103.5/094294).  ... 
doi:10.1109/cisda.2012.6291529 dblp:conf/cisda/De-la-TorreRGSG12 fatcat:p4p35bldw5dfxbn6ji7bdp6s6m

Progressive boosting for class imbalance and its application to face re-identification

Roghayeh Soleymani, Eric Granger, Giorgio Fumera
2018 Expert systems with applications  
For instance, in many video surveillance applications, e.g., face re-identification, the face individuals must be recognized over a distributed network of video cameras.  ...  An important challenge in such applications is class imbalance since the number of faces captured from an individual of interest is greatly outnumbered by those of others.  ...  Skewsensitive boolean combination for adaptive ensembles-an application to face recognition in video surveillance. Information Fusion, 20, 31-48.  ... 
doi:10.1016/j.eswa.2018.01.023 fatcat:wxoylnzcxzdmbh7g7zfm5hos6a

2020 Index IEEE Signal Processing Letters Vol. 27

2020 IEEE Signal Processing Letters  
., +, LSP 2020 1944-1948 Unsupervised Face Domain Transfer for Low-Resolution Face Recognition.  ...  ., +, LSP 2020 51-55 Gesture recognition Fast Adaptive Reparametrization (FAR) With Application to Human Action Recognition. Ghorbel, E., +, LSP 2020 580-584 Self-Similarity Action Proposal.  ... 
doi:10.1109/lsp.2021.3055468 fatcat:wfdtkv6fmngihjdqultujzv4by

State of the Art of Audio- and Video-Based Solutions for AAL

Slavisa ALeksic, Michael Atanasov, Jean Calleja Agius, Kenneth Camilleri, Anto Čartolovni, Pau Climent-Pérez, Sara Colantonio, Stefania Cristina, Vladimir Despotovic, Hazım Kemal Ekenel, Ekrem Erakin, Francisco Florez-Revuelta (+27 others)
2022 Zenodo  
In this respect, video- and audio-based AAL applications have several advantages, in terms of unobtrusiveness and information richness.  ...  They are designed to provide support in daily life in an invisible, unobtrusive and user-friendly manner.  ...  In [IV.14], authors used face registration algorithms [IV.114] for faces in front and profile view. Casalino et al. [IV.115] used an OpenCV Python library for face extraction from video frames.  ... 
doi:10.5281/zenodo.6390708 fatcat:6qfwqd2v2rhe5iuu5zgz77ay4i

The Multiclass ROC Front method for cost-sensitive classification

Simon Bernard, Clément Chatelain, Sébastien Adam, Robert Sabourin
2016 Pattern Recognition  
There is a need in that case to learn a classifier that can potentially suit to any of these costs in prediction phase.  ...  While this type of ROC-based multiobjective optimization approach has been successfully used for two-class problems, it has never been proposed in real-world multiclass classification problems.  ...  This boolean combination principle has also been recently used for face recognition in video surveillance in [26] .  ... 
doi:10.1016/j.patcog.2015.10.010 fatcat:xqpufytelra3lni27rlwtgtrtu

Automatic Face Understanding: Recognizing Families in Photos [article]

Joseph P Robinson
2021 arXiv   pre-print
Now, video dynamics, audio, and text captions can be used in the decision making of kinship recognition systems. We expect FIW will significantly impact research and reality.  ...  To address this, we introduced an objective that penalizes for low confidence. Another issue is a dependency on labeled data, which is expensive to collect and susceptible to error.  ...  Facial recognition, in itself, is applicable in a wide range of technologies.  ... 
arXiv:2102.08941v1 fatcat:eqje3jh23nb6do7crz7rw6342a

Reducing Efficiency of Connectivity-Splitting Attack on Newscast via Limited Gossip [chapter]

Jakub Muszyński, Sébastien Varrette, Pascal Bouvry
2016 Lecture Notes in Computer Science  
address a variety of applications ranging from searching and tracking to the surveillance of an area.  ...  are faced.  ... 
doi:10.1007/978-3-319-31204-0_20 fatcat:27rnwllk75cv5kncys2u7utreq

Transdisciplinary AI Observatory—Retrospective Analyses and Future-Oriented Contradistinctions

Nadisha-Marie Aliman, Leon Kester, Roman Yampolskiy
2021 Philosophies  
While both AS and EC acknowledge the need for a hybrid cognitive-affective approach to AI safety and overlap with regard to many short-term considerations, they differ fundamentally in the nature of multiple  ...  In the last years, artificial intelligence (AI) safety gained international recognition in the light of heterogeneous safety-critical and ethical issues that risk overshadowing the broad beneficial impacts  ...  Note that on the long-term this could in theory skew the unconscious internal model internet users exposed to more and more synthetic faces have of how human faces look like.  ... 
doi:10.3390/philosophies6010006 fatcat:mx4ex4hdgnfrfjdwyjmvewinga

A Novel Rebroadcast Technique for Reducing Routing Overhead In Mobile Ad Hoc Networks

Vinayak T Patil
2013 IOSR Journal of Computer Engineering  
This feature leads to frequent path failures and route reconstructions, which causes an increase in the routing control overhead. The overhead of a route discovery cannot be neglected.  ...  Thus, it is imperative to reduce the overhead of route discovery in the design of routing protocols of MANETs.  ...  Sitendra Tamrakar in writing this paper and giving the valuable suggestion.  ... 
doi:10.9790/0661-1260109 fatcat:jundvgfvpjcdpmtloz2z2w6ige

Transdisciplinary AI Observatory – Retrospective Analyses and Future-Oriented Contradistinctions [article]

Nadisha-Marie Aliman, Leon Kester, Roman Yampolskiy
2020 arXiv   pre-print
In the last years, AI safety gained international recognition in the light of heterogeneous safety-critical and ethical issues that risk overshadowing the broad beneficial impacts of AI.  ...  While both AS and EC acknowledge the need for a hybrid cognitive-affective approach to AI safety and overlap with regard to many short-term considerations, they differ fundamentally in the nature of multiple  ...  For instance, the deployment of AI for facial recognition of criminals based on "minute features" [84, 85] in their face is based on pseudo-scientific assumptions [86] .  ... 
arXiv:2012.02592v2 fatcat:q77hwo6xtfcczfwosotfpnvukq

Implementation of Fog computing for reliable E-health applications

Razvan Craciunescu, Albena Mihovska, Mihail Mihaylov, Sofoklis Kyriazakos, Ramjee Prasad, Simona Halunga
2015 2015 49th Asilomar Conference on Signals, Systems and Computers  
An important aspect is robust and resource efficient preamble design to minimize missed detection and false alarm probabilities of service requests.  ...  In this paper we compare one-stage and two-stage radio access protocol options tailored for sporadic transmissions of small data packets in uplink with respect to throughput and delay requirements.  ...  TP8b2-1 Object Recognition in Complex Video Scenes for Advertising Applications TP8b2-2 Fractal-Based Analysis for Foreground Detection TP8b2-3 Unsupervised Uncertainty Analysis for Video Saliency  ... 
doi:10.1109/acssc.2015.7421170 dblp:conf/acssc/CraciunescuMMKP15 fatcat:qm6mki5z6bcvrfimkmqjyrxaxm

Sentiment Analysis [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
Ensembles Ensembles are easily adapted to non-stationary data streams.  ...  classifiers, and adaptive ensembles that continuously react to changes in the stream.  ...  It might then be possible to learn, for example, that taking action action234 in state state42 is worth 6. 2 and leads to state state654321.  ... 
doi:10.1007/978-1-4899-7687-1_100512 fatcat:ce4yyqo2czftzcx2kbauglh3fu
« Previous Showing results 1 — 15 out of 66 results