Author

Peipei Song

h-index 4 View on Semantic Scholar

We have 3 of 14 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Multi-Faceted Evaluation and Mitigation of Emotion Hallucinations in MLLMs

Multimodal large language models (MLLMs) have shown strong potential in open-ended emotion understanding, yet they often generate emotion hallucinations. Evaluating such hallucinations is particularly challenging for two reasons. First, emotion understanding spans multiple cognitive facets, from multimodal perception t...

Bo-Wen Zeng, Pei-Pei Song, Wei-Dong Chen et al. · 0 citations

Preprint Aug 2026

ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing

ProFocus is a novel framework that models affective experience in artistic images via progressive visual focusing inspired by a hierarchical cognitive theory of human aesthetic appreciation and consistently outperforms state-of-the-art methods in both emotion recognition and affective explanation.

Zhiyan Zhang, Zi-Qing Yan, Jianqi Chen et al. · 0 citations

Jul 2026

MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos

MMHBench is introduced, a comprehensive multimodal benchmark for multi-perspective mental health understanding and a Multi-Agent Question Generation (MAQG) framework that simulates diverse social roles to synthesize questions from multiple perspectives.

Jinpeng Hu, Er-Qiang Wang, Shan A. Wang et al. · arXiv.org · 0 citations