MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning
This work provides a new benchmark dataset for multimodal emotion recognition, particularly benefiting the Chinese research community, but it is incremental as it builds on existing challenge formats without introducing novel methods.
The paper introduces the Multimodal Emotion Recognition Challenge (MER 2023), which tackles the problem of system robustness in emotion recognition by organizing three tracks focused on multi-label learning, modality robustness with noise, and semi-supervised learning, resulting in a new benchmark dataset for the Chinese research community.
The first Multimodal Emotion Recognition Challenge (MER 2023) was successfully held at ACM Multimedia. The challenge focuses on system robustness and consists of three distinct tracks: (1) MER-MULTI, where participants are required to recognize both discrete and dimensional emotions; (2) MER-NOISE, in which noise is added to test videos for modality robustness evaluation; (3) MER-SEMI, which provides a large amount of unlabeled samples for semi-supervised learning. In this paper, we introduce the motivation behind this challenge, describe the benchmark dataset, and provide some statistics about participants. To continue using this dataset after MER 2023, please sign a new End User License Agreement and send it to our official email address merchallenge.contact@gmail.com. We believe this high-quality dataset can become a new benchmark in multimodal emotion recognition, especially for the Chinese research community.