2 papers
cs.CV2024
Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement
Zheng Yuan, Jie Zhang, Yude Wang +2
The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods,…
cs.CV2024
Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading
Songtao Luo, Shuang Yang, Shiguang Shan +1
In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker's own characteristics can always be portrayed well…