Parallel session 23

Multimodal Systems
Room – Odessos Hall; Chair – Salmane Chafik
15.10-15.30Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning (Jordan Konstantinov Kralev)
15.30-15.50Performance Gaps in Acted and Naturalistic Speech: Insights from Speech Emotion Recognition Strategies on Customer Service Calls (Lily Kawaoto, Hita Gupta, Ning Yu and Daniel Dakota)
15.50-16.10Visual Priming Effect on Large-scale Vision Language Models (Daiki Yoshida, Haruki Sakajo, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe)
Check related remoted pre-recorded presentations or papers in Proceedings:
(short) Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil (Nevidu Jayatilleke and Nisansa de Silva)
Scroll to Top