Apparent personality analysis from short videos poses significant chal-lenges due to the complex interplay of visual, auditory, and textual cues. In this paper, we propose GAME, a Graph-Augmented Multimodal Encoder designed to robustly model and fuse multi-source features for automatic personality prediction. For the visual stream, we construct a facial graph and introduce a dual-branch Geo Two-Stream Network, which combines Graph Convolutional Networks (GCNs) and Convolutional Neural Net-works (CNNs) with attention mechanisms to capture both structural and appearance-based facial cues. Complementing this, global context and iden-tity features are extracted using pretrained ResNet18 and VGGFace back-bones. To capture temporal dynamics, frame-level features are processed by a BiGRU enhanced with temporal attention modules. Meanwhile, audio representations are derived from the VGGish network, and linguistic se-mantics are captured via the XLM-Roberta transformer. To achieve effective multimodal integration, we propose a Channel Attention-based Fusion module, followed by a Multi-Layer Perceptron (MLP) regression head for predicting personality traits. Extensive experiments show that GAME con-sistently outperforms existing methods across multiple benchmarks, vali-dating its effectiveness and generalizability.
@article{arxiv.2505.03846,
title = {GAME: Learning Multimodal Interactions via Graph Structures for Personality Trait Estimation},
author = {Kangsheng Wang and Yuhang Li and Chengwei Ye and Yufei Lin and Huanzhen Zhang and Bohan Hu and Linuo Xu and Shuyan Liu},
journal= {arXiv preprint arXiv:2505.03846},
year = {2025}
}
Comments
The article contains serious scientific errors and cannot be corrected by updating the preprint