Identity unbiased deception detection by 2D-to-3D face reconstruction

buir.contributor.authorMandıra, Burak
buir.contributor.authorDibeklioğlu, Hamdi
dc.citation.epage154en_US
dc.citation.spage145en_US
dc.contributor.authorNgô, Le Minh
dc.contributor.authorWang, Wei
dc.contributor.authorMandıra, Burak
dc.contributor.authorKaraoğlu, Sezer
dc.contributor.authorBouma, Henri
dc.contributor.authorDibeklioğlu, Hamdi
dc.contributor.authorGevers, Theo
dc.coverage.spatialWaikoloa, HI, USAen_US
dc.date.accessioned2022-02-09T07:48:34Z
dc.date.available2022-02-09T07:48:34Z
dc.date.issued2021-06-14
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionConference Name: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)en_US
dc.descriptionDate of Conference: 3-8 January 2021en_US
dc.description.abstractDeception is a common phenomenon in society, both in our private and professional lives. However, humans are notoriously bad at accurate deception detection. Based on the literature, human accuracy of distinguishing between lies and truthful statements is 54% on average, in other words, it is slightly better than a random guess. While people do not much care about this issue, in high-stakes situations such as interrogations for series crimes and for evaluating the testimonies in court cases, accurate deception detection methods are highly desirable. To achieve a reliable, covert, and non-invasive deception detection, we propose a novel method that disentangles facial expression and head pose related features using 2D-to-3D face reconstruction technique from a video sequence and uses them to learn characteristics of deceptive behavior. We evaluate the proposed method on the Real-Life Trial (RLT) dataset that contains high-stakes deceits recorded in courtrooms. Our results show that the proposed method (with an accuracy of 68%) improves the state of the art. Besides, a new dataset has been collected, for the first time, for low-stake deceit detection. In addition, we compare high-stake deceit detection methods on the newly collected low-stake deceits.en_US
dc.description.provenanceSubmitted by Betül Özen (ozen@bilkent.edu.tr) on 2022-02-09T07:48:34Z No. of bitstreams: 1 Identity_Unbiased_Deception_Detection_by_2D-to-3D_Face_Reconstruction.pdf: 5850994 bytes, checksum: 73d106b01a2661f76409872213f8b463 (MD5)en
dc.description.provenanceMade available in DSpace on 2022-02-09T07:48:34Z (GMT). No. of bitstreams: 1 Identity_Unbiased_Deception_Detection_by_2D-to-3D_Face_Reconstruction.pdf: 5850994 bytes, checksum: 73d106b01a2661f76409872213f8b463 (MD5) Previous issue date: 2021-06-14en
dc.identifier.doi10.1109/WACV48630.2021.00019en_US
dc.identifier.eisbn978-1-6654-0477-8en_US
dc.identifier.eissn2642-9381en_US
dc.identifier.isbn978-1-6654-4640-2en_US
dc.identifier.issn2472-6737en_US
dc.identifier.urihttp://hdl.handle.net/11693/77151en_US
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/WACV48630.2021.00019en_US
dc.source.titleIEEE Workshop on Applications of Computer Vision (WACV)en_US
dc.titleIdentity unbiased deception detection by 2D-to-3D face reconstructionen_US
dc.typeConference Paperen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Identity_Unbiased_Deception_Detection_by_2D-to-3D_Face_Reconstruction.pdf
Size:
5.58 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description: