2 papers
cs.CV2026
Robust Embodied Perception in Dynamic Environments via Disentangled Weight Fusion
Juncen Guo, Xiaoguang Zhu, Jingyi Wu +4
Embodied perception systems face severe challenges of dynamic environment distribution drift when they continuously interact in open physical spaces. However, the existing domain i…
cs.SD2023
On the Audio-visual Synchronization for Lip-to-Speech Synthesis
Zhe Niu, Brian Mak
Most lip-to-speech (LTS) synthesis models are trained and evaluated under the assumption that the audio-video pairs in the dataset are perfectly synchronized. In this work, we show…