4 papers
Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition
Keito Inoshita, Takato Ueno
Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distribution shift. Crucially, thes…
Bayesian Spectral Emotion Transition Discovery from Multi-Annotator Disagreement
Keito Inoshita, Takato Ueno
Emotions evolve through the dynamics of conversation, and understanding their transition structure is foundational to applications ranging from mental-health screening to dialogue…
Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP
Keito Inoshita, Takato Ueno
Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in subjective NLP. Yet no prior…
A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing
Takato Ueno, Keito Inoshita
Japan's kairanban culture and idobata conversations have long functioned as traditional communication practices that foster nuanced dialogue among community members and contribute…