502 citations · 2.5k across the 78 of their papers we have counts for
78 papers
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,…
Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues
Feixiang Wang, Shuang Yang, Shiguang Shan +1
In this work, we focus on leveraging facial cues beyond the lip region for robust Audio-Visual Speech Enhancement (AVSE). The facial region, encompassing the lip region, reflects a…
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…
Dual Compensation Residual Networks for Class Imbalanced Learning
Ruibing Hou, Hong Chang, Bingpeng Ma +2
Learning generalizable representation and classifier for class-imbalanced data is challenging for data-driven deep models. Most studies attempt to re-balance the data distribution,…
Function-Consistent Feature Distillation
Dongyang Liu, Meina Kan, Shiguang Shan +1
Feature distillation makes the student mimic the intermediate features of the teacher. Nearly all existing feature-distillation methods use L2 distance or its slight variants as th…
Diversity-Measurable Anomaly Detection
Wenrui Liu, Hong Chang, Bingpeng Ma +2
Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not wel…