FDCA-CLIP: Frequency-Enhanced Dual-Semantic Cross-Modal Alignment for Zero-Shot Spatio-Temporal Action Localization
FDCA-CLIP: Frequency-Enhanced Dual-Semantic Cross-Modal Alignment for Zero-Shot Spatio-Temporal Action Localization
Xing Li,Jian Cai,2 Authors,Xin Li
2026 · DOI: 10.1109/icassp55912.2026.11463002
IEEE International Conference on Acoustics, Speech, and Signal Processing · 0 Citations