{"ID":2859848,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04753","arxiv_id":"2510.04753","title":"Beyond Appearance: Transformer-based Person Identification from Conversational Dynamics","abstract":"This paper investigates the performance of transformer-based architectures for person identification in natural, face-to-face conversation scenario. We implement and evaluate a two-stream framework that separately models spatial configurations and temporal motion patterns of 133 COCO WholeBody keypoints, extracted from a subset of the CANDOR conversational corpus. Our experiments compare pre-trained and from-scratch training, investigate the use of velocity features, and introduce a multi-scale temporal transformer for hierarchical motion modeling. Results demonstrate that domain-specific training significantly outperforms transfer learning, and that spatial configurations carry more discriminative information than temporal dynamics. The spatial transformer achieves 95.74% accuracy, while the multi-scale temporal transformer achieves 93.90%. Feature-level fusion pushes performance to 98.03%, confirming that postural and dynamic information are complementary. These findings highlight the potential of transformer architectures for person identification in natural interactions and provide insights for future multimodal and cross-cultural studies.","short_abstract":"This paper investigates the performance of transformer-based architectures for person identification in natural, face-to-face conversation scenario. We implement and evaluate a two-stream framework that separately models spatial configurations and temporal motion patterns of 133 COCO WholeBody keypoints, extracted from...","url_abs":"https://arxiv.org/abs/2510.04753","url_pdf":"https://arxiv.org/pdf/2510.04753v1","authors":"[\"Masoumeh Chapariniya\",\"Teodora Vukovic\",\"Sarah Ebling\",\"Volker Dellwo\"]","published":"2025-10-06T12:31:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}