Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind
PIP-ToM with GPT-4o outperforms existing ToM methods across MuMA-ToM, MMToM-QA, and Hi-ToM, achieving average accuracies of 92.56%, 95.00%, and 95.00%, respectively.
Zi-Qi Liao, Jia-Qi Shen, Yi-Ming Na et al.
· 0 citations