Search papers, labs, and topics across Lattice.
Hefei University of Technology (HFUT)
3
0
4
Cross-Modal Pseudo-Labeling boosts micro-gesture recognition performance, bridging the gap between subjects and enhancing model robustness.
Fusing RGB and skeleton data with a gated residual module boosts micro-gesture recognition accuracy, revealing the power of multi-modal integration in emotion analysis.
Achieve better image quality in Diffusion Transformers without extra training by dynamically trading off compute and cache risk.
