Sparsity in Dynamics of Spontaneous Subtle Emotions: Analysis and Application
Sparsity in Dynamics of Spontaneous Subtle Emotions: Analysis and Application
复制标题
DOI：
10.1109/taffc.2016.2523996
复制
发表时间：
2017-07-01
影响因子：
11.2
通讯作者：
Phan, Raphael C. -W.
中科院分区：
文献类型：
--
作者：
Anh Cat Le Ngo;See, John;Phan, Raphael C. -W.
微妙的情绪存在于各种现实生活中：在敌对的环境中，敌人和/或间谍恶意地隐藏他们的情绪，作为他们欺骗的一部分;在生命受到威胁的情况下，受害者别无选择，只能保持他们的真实的感受;在医疗现场，患有抑郁症等心理疾病的患者可能有意或潜意识地抑制他们对亲人的痛苦。在这种情况下，在为时已晚之前认识到这些微妙的情绪往往是至关重要的。这些自发的微妙情绪通常通过微表情来表达，微表情是面部肌肉的微小、突然和短暂的动态;因此，这样的微表情对视觉识别提出了很大的挑战。识别任务的突然但重要的动态在时间上是稀疏的，而其余的，即不相关的动态，在时间上是冗余的。在这项工作中，我们分析和执行稀疏性约束，以学习重要的时间和频谱结构，同时消除微表情的不相关的面部动态，这将减轻自发微妙情绪的视觉识别的挑战。通过在CASME II和SMIC这两个成熟的公开的自发微妙情感数据库上进行的几个稀疏度水平的自动自发微妙情感识别的实验结果证实了这一假设。当仅保留原始序列的显著动态时，自动细微情感识别的整体性能得到提升。
Subtle emotions are present in diverse real-life situations: in hostile environments, enemies and/or spies maliciously conceal their emotions as part of their deception; in life-threatening situations, victims under duress have no choice but to with hold their real feelings; in the medical scene, patients with psychological conditions such as depression could either be intentionally or subconsciously suppressing their anguish from loved ones. Under such circumstances, it is often crucial that these subtle emotions are recognized before it is too late. These spontaneous subtle emotions are typically expressed through micro-expressions, which are tiny, sudden and short-lived dynamics of facial muscles; thus, such micro-expressions pose a great challenge for visual recognition. The abrupt but significant dynamics for the recognition task are temporally sparse while the rest, i.e. irrelevant dynamics, are temporally redundant. In this work, we analyze and enforce sparsity constraints to learn significant temporal and spectral structures while eliminating irrelevant facial dynamics of micro-expressions, which would ease the challenge in the visual recognition of spontaneous subtle emotions. The hypothesis is confirmed through experimental results of automatic spontaneous subtle emotion recognition with several sparsity levels on CASME II and SMIC, the two well-established and publicly available spontaneous subtle emotion databases. The overall performances of the automatic subtle emotion recognition are boosted when only significant dynamics of the original sequences are preserved.