Quantified Facial Temporal-Expressiveness Dynamics for Affect Analysis
This work addresses the need for efficient quantification in automated affect modeling systems, particularly for applications like pain analysis, but it appears incremental as it builds on existing multimodal feature approaches.
The paper tackled the problem of quantifying facial expressiveness for affect analysis by proposing a method called facial Temporal-expressiveness Dynamics (TED), which leverages multimodal features to measure expressiveness, and demonstrated its efficacy in a case study on spontaneous pain using the UNBC-McMaster dataset.
The quantification of visual affect data (e.g. face images) is essential to build and monitor automated affect modeling systems efficiently. Considering this, this work proposes quantified facial Temporal-expressiveness Dynamics (TED) to quantify the expressiveness of human faces. The proposed algorithm leverages multimodal facial features by incorporating static and dynamic information to enable accurate measurements of facial expressiveness. We show that TED can be used for high-level tasks such as summarization of unstructured visual data, and expectation from and interpretation of automated affect recognition models. To evaluate the positive impact of using TED, a case study was conducted on spontaneous pain using the UNBC-McMaster spontaneous shoulder pain dataset. Experimental results show the efficacy of using TED for quantified affect analysis.