國立虎尾科技大學 |

Language: English

Back

Adversarial Autoencoders for Anomalo...

ProQuest Information and Learning Co.

Adversarial Autoencoders for Anomalous Event Detection in Images.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Adversarial Autoencoders for Anomalous Event Detection in Images./
Author:	Dimokranitou, Asimenia.
Description:	1 online resource (41 pages)
Notes:	Source: Masters Abstracts International, Volume: 56-06.
Contained By:	Masters Abstracts International56-06(E).
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780355188110

Adversarial Autoencoders for Anomalous Event Detection in Images.
Dimokranitou, Asimenia.

Adversarial Autoencoders for Anomalous Event Detection in Images. - 1 online resource (41 pages)

Source: Masters Abstracts International, Volume: 56-06.

Thesis (M.S.)

Includes bibliographical references

Detection of anomalous events in image sequences is a problem in computer vision with various applications, such as public security, health monitoring and intrusion detection. Despite the various applications, anomaly detection remains an ill-defined problem. Several definitions exist, the most commonly used defines an anomaly as a low probability event. Anomaly detection is a challenging problem mainly because of the lack of abnormal observations in the data. Thus, usually it is considered an unsupervised learning problem. Our approach is based on autoencoders in combination with Generative Adversarial Networks. The method is called Adversarial Autoencoders, and it is a probabilistic autoencoder, that attempts to match the aggregated posterior of the hidden code vector of the autoencoder, with an arbitrary prior distribution. The adversarial error of the learned autoencoder is low for regular events and high for irregular events. We compare our approach with state of the art methods and describe our results with respect to accuracy and efficiency.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355188110Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Adversarial Autoencoders for Anomalous Event Detection in Images.
LDR:02288ntm a2200337Ki 4500 001 910750
005 20180517112609.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355188110
035 $a (MiAaPQ)AAI10275251
035 $a (MiAaPQ)purdue:21440
035 $a AAI10275251
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Dimokranitou, Asimenia. $3 1182198
245 1 0 $a Adversarial Autoencoders for Anomalous Event Detection in Images.
264 0 $c 2017
300 $a 1 online resource (41 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 56-06.
500 $a Adviser: Gavriil Tsechpenakis.
502 $a Thesis (M.S.) $c Purdue University $d 2017.
504 $a Includes bibliographical references
520 $a Detection of anomalous events in image sequences is a problem in computer vision with various applications, such as public security, health monitoring and intrusion detection. Despite the various applications, anomaly detection remains an ill-defined problem. Several definitions exist, the most commonly used defines an anomaly as a low probability event. Anomaly detection is a challenging problem mainly because of the lack of abnormal observations in the data. Thus, usually it is considered an unsupervised learning problem. Our approach is based on autoencoders in combination with Generative Adversarial Networks. The method is called Adversarial Autoencoders, and it is a probabilistic autoencoder, that attempts to match the aggregated posterior of the hidden code vector of the autoencoder, with an arbitrary prior distribution. The adversarial error of the learned autoencoder is low for regular events and high for irregular events. We compare our approach with state of the art methods and describe our results with respect to accuracy and efficiency.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Purdue University. $b Computer Sciences. $3 1179390
773 0 $t Masters Abstracts International $g 56-06(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10275251 $z click for full text (PQDT)

based on 0 review(s)

Multimedia

Reviews

Add a review and share your thoughts with other readers

Export

pickup library