Bi-modal First Impressions Recognition Using Temporally Ordered Deep Audio and Stochastic Visual Features
Bi-modal First Impressions Recognition Using Temporally Ordered Deep Audio and Stochastic Visual Features
复制标题
DOI：
10.1007/978-3-319-49409-8_27
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Arulkumar Subramaniam;V. Patel;Ashish Mishra;P. Balasubramanian;Anurag Mittal
中科院分区：
文献类型：
--
作者：
Arulkumar Subramaniam;V. Patel;Ashish Mishra;P. Balasubramanian;Anurag Mittal
提出了一种基于短视频中大五人格特征的第一印象识别方法。大五人格特质（Big Five Personality Traits）是一个描述人类人格的模型，使用五个大类：外向性，可接受性，尽责性，神经质和开放性。我们使用时间排序的音频和来自几帧的新的随机视觉特征来训练两个双模态端到端深度神经网络架构，而不会过度拟合。我们的经验表明，训练后的模型表现非常好，即使是在从一小部分输入中训练之后。我们的方法在ChaLearn 2016年的外观人格分析（阿帕）比赛中使用ChaLearn APA2016数据集进行评估，并取得了优异的性能。
We propose a novel approach for First Impressions Recognition in terms of the Big Five personality-traits from short videos. The Big Five personality traits is a model to describe human personality using five broad categories: Extraversion, Agreeableness, Conscientiousness, Neuroticism and Openness. We train two bi-modal end-to-end deep neural network architectures using temporally ordered audio and novel stochastic visual features from few frames, without over-fitting. We empirically show that the trained models perform exceptionally well, even after training from a small sub-portions of inputs. Our method is evaluated in ChaLearn LAP 2016 Apparent Personality Analysis (APA) competition using ChaLearn LAP APA2016 dataset and achieved excellent performance.