2 papers
cs.SD2026
MG-Former: A Transformer-Based Framework for Music-Driven 3D Conducting Gesture Generation
Ke Qiu, Yawen Qin, Tianzhi Jia +3
Generating expressive conducting gestures from music is a challenging cross-modal motion synthesis problem: the output must follow long-range musical structure, preserve beat-level…
cs.MM2026
CustomDancer: Customized Dance Recommendation by Text-Dance Retrieval
Yawen Qin, Ke Qiu, Qin Zhang
Dance serves as both a cultural cornerstone and a medium for personal expression, yet the rapid growth of online dance content has made personalized discovery increasingly difficul…