arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.10058cs.AIcs.MM
收藏

是LeVAsa不是LevioSA!价-唤醒结构排列的潜在编码

It's LeVAsa not LevioSA! Latent Encodings for Valence-Arousal Structure Alignment

IIIT Delhi(德里印德拉普拉斯塔信息技术学院)

Surabhi S. Nath, Vishaal Udandarao, Jainendra Shukla

摘要:

近年来,情感计算领域取得了长足的进步。已经开发了几种模型来表示和量化情绪。两种流行的模型包括:(i)将情绪表示为离散标签的分类模型,以及(ii)将情绪表示为Valence-Arousal(VA)环域的维度模型。然而,这两种标记方法之间的注释映射没有标准。我们建立了一个新的算法,用于映射分类和维度模型标签,使用跨情感面部图像数据集的注释传输。此外,我们利用转移的注释学习丰富的和可解释的数据表示使用变分自编码器(VAE)。我们提出了“LeVAsa”,这是一个VAE模型,它通过将潜在空间与VA空间对齐来学习隐式结构。我们通过对两个基准情感图像数据集进行定量和定性分析,比较与Vanilla VAE的性能,评估LeVAsa的疗效。我们的研究结果表明,LeVAsa实现了高潜在的回旋对齐,从而改善了下游分类情感预测。这项工作还展示了对齐程度和重建质量之间的权衡。

英文摘要:

In recent years, great strides have been made in the field of affective computing. Several models have been developed to represent and quantify emotions. Two popular ones include (i) categorical models which represent emotions as discrete labels, and (ii) dimensional models which represent emotions in a Valence-Arousal (VA) circumplex domain. However, there is no standard for annotation mapping between the two labelling methods. We build a novel algorithm for mapping categorical and dimensional model labels using annotation transfer across affective facial image datasets. Further, we utilize the transferred annotations to learn rich and interpretable data representations using a variational autoencoder (VAE). We present "LeVAsa", a VAE model that learns implicit structure by aligning the latent space with the VA space. We evaluate the efficacy of LeVAsa by comparing performance with the Vanilla VAE using quantitative and qualitative analysis on two benchmark affective image datasets. Our results reveal that LeVAsa achieves high latent-circumplex alignment which leads to improved downstream categorical emotion prediction. The work also demonstrates the trade-off between degree of alignment and quality of reconstructions.

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。

↑