Co-speech gestures serve essential pragmatic functions in human communication, yet current computational efforts predominantly prioritize black-box detection or generation quality over mechanistic transparency. As a result, the cross-modal organization of these functions remains largely unexplored. In this paper, we sh...
Jin-Qian Zhang, Si-Xia Li, C. Mawalim et al.· Proceedings of the 28th Inte...· 0 citations
The MultiMediate'26 challenge is described and its goals are described, the NoXi, NoXi-J, MPIIGI, and PInSoRo datasets are introduced, extracted multi-modal features are presented, and the baseline model for engagement estimation across all domains is presented.
Marius Funk, Daksitha Senel Withanage Don, Michal Balazia et al.· Proceedings of the 34th ACM...· 4 citations
Co-speech gestures serve essential pragmatic functions in human communication, yet current computational efforts predominantly prioritize black-box detection or generation quality over mechanistic transparency. As a result, the cross-modal organization of these functions remains largely unexplored. In this paper, we sh...
Jin-Qian Zhang, Si-Xia Li, C. Mawalim et al.· 0 citations
This work examines whether FVs extracted from a source language can steer task behavior in another language under both standard clean and perturbed zero-shot settings without providing demonstrations during inference, and observes that each LLM exhibits a relatively stable optimal range of attention heads for construct...
Jieying Xue, Phuong Minh Nguyen, Minh-Quang Le Nguyen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.