Temporal Convolution Networks with Positional Encoding for Evoked Expression Estimation
This work addresses the domain-specific challenge of evoked expression estimation from videos, providing an incremental improvement in performance for applications like emotion analysis.
The paper tackled the problem of predicting evoked facial expressions from video by using pre-trained models for feature extraction and a temporal convolution network with positional encoding to handle missing annotations, achieving state-of-the-art results with a Pearson correlation coefficient of 0.05477 in the EEV 2021 challenge.
This paper presents an approach for Evoked Expressions from Videos (EEV) challenge, which aims to predict evoked facial expressions from video. We take advantage of pre-trained models on large-scale datasets in computer vision and audio signals to extract the deep representation of timestamps in the video. A temporal convolution network, rather than an RNN like architecture, is used to explore temporal relationships due to its advantage in memory consumption and parallelism. Furthermore, to address the missing annotations of some timestamps, positional encoding is employed to ensure continuity of input data when discarding these timestamps during training. We achieved state-of-the-art results on the EEV challenge with a Pearson correlation coefficient of 0.05477, the first ranked performance in the EEV 2021 challenge.