3 papers
cs.CV2026
UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios
Ruidi Fan, Yang Zhou, Siyuan Wang +3
Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing. However, current methods have fundamental d…
cs.CV2026
SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition
Rui Fan, Weidong Hao
Event cameras action recognition (EAR) offers compelling privacy-protecting and efficiency advantages, where temporal motion dynamics is of great importance. Existing spatiotempora…
cs.CV2025
EGTM: Event-guided Efficient Turbulence Mitigation
Huanan Li, Rui Fan, Juntao Guan +5
Turbulence mitigation (TM) aims to remove the stochastic distortions and blurs introduced by atmospheric turbulence into frame cameras. Existing state-of-the-art deep-learning TM m…