DGC-Net: Cross-Modal Dynamic Routing with Global-Guided Compensation in Multimodal Sentiment Analysis
DGC-Net mitigates cross-modal affective cue inconsistency through cross-modal contribution-aware dynamic expert routing and alleviates sample-dependent global-local contribution imbalance while preserving global semantic as the primary anchor and adaptively incorporating expert-refined local cues.
Li-Nan Zhu, Huai-Jing Wu, Xiao Han et al.
· 0 citations