Please wait ...
0% Complete
Home
/
15th International Conference on Computer and Knowledge Engineering
Beyond Appearance: Transformer-based Person Identification from Conversational Dynamics
Authors :
Masoumeh Chapariniya
1
Teodora Vukovic
2
Sarah Ebling
3
Volker Dellwo
4
1- University of Zurich
2- university of zurich
3- university of zurich
4- university of zurich
Keywords :
Person identification،conversational gestures،vision transformers،spatial-temporal modeling،keypoint 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
Papers List
List of archived papers
Attention Transfer in Self-Regulated Networks for Recognizing Human Actions from Still Images
Masoumeh Chapariniya - Sara Vesali Barazande - Seyed Sajad Ashrafi - Shahriar B.Shokouhi
Fatty Liver Level Recognition Using Particle Swarm Optimization (PSO) Image Segmentation and Analysis
Seyed Muhammad Hossein Mousavi - Vyacheslav Lyashenko - Atiye Ilanloo - S. Younes Mirinezhad
Pyramid Transformer for Traffic Sign Detection
Omid Nejati manzari - Amin Boudesh - Shahriar B. Shokouhi
HV-RCE: Reducing Network Bandwidth Usage for Video Transmission via HEVC/VVC Features in Resource-Constrained Environments
Yaghoub Saberi - Mohammadreza Forghani - Sharifeh Sadat Mirkhalaf
Iris Detection and Segmentation Using Deep Learning
Ali Khaki - Ali Aghagolzadeh - Bagher Rahimpour Cami
Dynamic Knowledge Enhanced Neural Fashion Trend Forecasting with Quantile Loss
Fatemeh Rooholamini - Reza Azmi - Mobina Khademhossein - Maral Zarvani
Adaptive Ensemble Learning for Software Defect Prediction: A Dynamic Weighted Hybrid Model Using SVM, DT, and ANFIS-PSO
Mohsen EsfandyariDoulabi - Amin Esfandiyari Doulabi - Javad Khaligh
Leveraging the Power of Object Detection Models in Identifying Litter for a Significant Reduction in Environmental Pollution
Lim Zhen Xian - Ervin Gubin Moung - Jason Teo Tze Wi - Nordin Saad - Farashazillah Yahya - Tiong Lin Rui - Ali Farzamnia
Taguchi Design of Experiments Application in Robust sEMG Based Force Estimation
Mohsen Ghanaei - Hadi Kalani - Alireza Akbarzadeh
Multi-Task Transformer for Stock Market Trend Prediction
Seyed Morteza Mirjebreili - Ata Solouki - Hamidreza Soltanalizadeh - Mohammad Sabokrou
more
Samin Hamayesh - Version 46.0.2