Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event Cameras
This work introduces Emo-DVS, the first large-scale event-based emotion analysis dataset, which couples dynamic illumination with the Facial Action Unit (FAU) subset and emotion subset and proposes the Information-Guided Gated Fusion (IGF) framework, which achieves state-of-the-art performance.
Jia-Qi Chen, Qin-Fu Xu, Hao Zhuang et al.
· 0 citations