Audio-visual generalized zero-shot learning leverages the synergy between auditory and visual modalities to recognize instances from seen and unseen categories. However, existing methods usually rely on a rigid alignment paradigm, mapping complex multi-modal features to singular class category. This leads to semantic i...
Bao-Yuan Gao, Shi-Guang Liu· Proceedings of the 34th ACM...· 0 citations
This work introduces MBench, a comprehensive benchmark for zero-shot compositional motion understanding, and introduces a systematic scaling strategy—synchronously expanding training data diversity and model capacity across architectures like TMR and MoPa—to confirm that synergistically scaling data and capacity is ind...
Wan-Li Ma, En-Yun Xuan, Teng-Fei Li et al.· Proceedings of the 34th ACM...· 0 citations
Recently, the use of data-driven approaches to accelerate physical simulation has emerged as a prominent research frontier. However, existing methodologies often grapple with limitations such as constrained generalization capabilities, a lack of physical consistency, and performance that falls significantly short of re...
Qi-Tong Wu, Bo Li, Shi-Guang Liu· IEEE Transactions on Visuali...· 0 citations
Speech‐driven 3D facial animation has broad applications in virtual reality, film production, and digital human generation. Personalized style expression plays a crucial role in enhancing realism and expressiveness. However, existing approaches often focus on either emotional expression or speaking style in isolation...