arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.00344cs.CLcs.AIcs.CV
收藏

一种用于多模态欺骗检测的深度学习方法

A Deep Learning Approach for Multimodal Deception Detection

A*STAR Artificial Intelligence Initiative (A*AI), Institute of High Performance Computing(新加坡科技研究局人工智能计划(A*AI),高性能计算研究所);Centro de Investigacin en Computacin, IPN(墨西哥国立理工学院计算研究中心);Temasek Laboratories, Nanyang Technological University(南洋理工大学淡马锡实验室);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院)

Gangeshwar Krishnamurthy, Navonil Majumder, Soujanya Poria, Erik Cambria

摘要:

自动欺骗检测是计算语言学中的一个重要研究课题,由于其潜在的应用前景而受到广泛关注。在本文中,我们提出了一个简单但难以击败的多模态神经模型的欺骗检测。通过将视频、音频和文本等不同形式的特征与微表情特征相结合,我们证明了在现实生活中的视频中检测欺骗可以更准确。在真实欺骗视频数据集上的实验结果表明,该模型的欺骗检测准确率为96.14%,ROC-AUC为0.9799,优于现有技术。

英文摘要:

Automatic deception detection is an important task that has gained momentum in computational linguistics due to its potential applications. In this paper, we propose a simple yet tough to beat multi-modal neural model for deception detection. By combining features from different modalities such as video, audio, and text along with Micro-Expression features, we show that detecting deception in real life videos can be more accurate. Experimental results on a dataset of real-life deception videos show that our model outperforms existing techniques for deception detection with an accuracy of 96.14% and ROC-AUC of 0.9799.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑