TY - GEN
T1 - Skeletons on the Stairs
T2 - 28th International Conference on Neural Information Processing, ICONIP 2021
AU - Li, Yiran
AU - Liu, Yang
AU - Qin, Zhenyue
AU - Zhu, Xuanying
AU - Caldwell, Sabrina
AU - Gedeon, Tom
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - Physiological signals have been widely applied for deception detection. However, these signals are usually collected by devices attached to subjects. Such attachments can cause discomfort and unexpected anxiety, and thus will be noticed. Alternatively, skeleton-based gait data collected in a non-contact setting can be a solution to detect deception. Therefore, in this paper, we aim to investigate whether liars can be recognized using their skeletal motion trajectories. We extract skeletal gait data from videos of participants going up and downstairs after they conduct a mock crime. With the extracted skeletal gait data, a simplified version of Multi-Scale Graph 3D (MS-G3D) network is able to recognise participants’ deceptive behaviour with an average accuracy of 70.9%. This result is higher than those obtained from traditional classifiers such as neural networks, support vector machines and decision trees, which are trained on hand-crafted features calculated from the gait data.
AB - Physiological signals have been widely applied for deception detection. However, these signals are usually collected by devices attached to subjects. Such attachments can cause discomfort and unexpected anxiety, and thus will be noticed. Alternatively, skeleton-based gait data collected in a non-contact setting can be a solution to detect deception. Therefore, in this paper, we aim to investigate whether liars can be recognized using their skeletal motion trajectories. We extract skeletal gait data from videos of participants going up and downstairs after they conduct a mock crime. With the extracted skeletal gait data, a simplified version of Multi-Scale Graph 3D (MS-G3D) network is able to recognise participants’ deceptive behaviour with an average accuracy of 70.9%. This result is higher than those obtained from traditional classifiers such as neural networks, support vector machines and decision trees, which are trained on hand-crafted features calculated from the gait data.
KW - Deception detection
KW - GCN
KW - Skeleton-based gait data
UR - http://www.scopus.com/inward/record.url?scp=85121909601&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-92310-5_23
DO - 10.1007/978-3-030-92310-5_23
M3 - Conference contribution
SN - 9783030923099
T3 - Communications in Computer and Information Science
SP - 194
EP - 202
BT - Neural Information Processing - 28th International Conference, ICONIP 2021, Proceedings
A2 - Mantoro, Teddy
A2 - Lee, Minho
A2 - Ayu, Media Anugerah
A2 - Wong, Kok Wai
A2 - Hidayanto, Achmad Nizar
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 8 December 2021 through 12 December 2021
ER -