CHECK OUT MY LATEST PUBLICATION

Bryant, D., Deng, S., Sephus, N., Xia, W., and Perona, P. (2022). Multi-Dimensional, Nuanced and Subjective – Measuring the Perception of Facial Expressions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (to appear in CVPR ’22).

• We propose a novel method to collect and model facial expression perception that measures both expression intensity and ambiguity.

• We curated a diverse dataset of in-the-wild face images and collected multi-dimensional, modulated annotations along 6, 15, and 21 expression dimensions.

• We present an algorithmic benchmark that considers the underlying distribution of facial expression perception and assesses the performance of 4 state-of-the-art algorithms.