Affect-Prototype Guided Fusion for Open-Vocabulary Incomplete Multi-modal Emotion Recognition
An Affect-Prototype-Conditioned Fusion (APCF) framework for incomplete open-vocabulary emotion recognition is proposed, which extends modal contribution learning to scenarios guided by arbitrary emotional semantics and substantially outperforms state-of-the-art baselines.
Yi-Chi Zhang, Shen-Yue Wang, Jing Luo et al.
· 0 citations