Mask Biasing
Mask Biasing is a methodological technique in computational modeling and image processing that systematically adjusts the spatial or feature-level attention of a mask to prioritize specific regions or attributes during analysis, thereby distinguishing it from neutral or uniform masking approaches by introducing deliberate, asymmetric constraints to influence model behavior or outcomes.
15
Publications
294
Citations
50
Authors
16
Institutions
Publications per year
2017–2026
6
Parents
15
PLFace: Progressive Learning for Face Recognition with Mask Bias
Baojin Huang, Zhongyuan Wang, Guangcheng Wang et al. · Pattern Recognition · 2022 · 39 citations · Full text
The geometry of masking in neural populations
Dario L. Ringach · Nature Communications · 2019 · 24 citations · Full text
Medicine, Neurobiology, Neuroscience +17
1–5 of 15
50
3
h-index
2
h-index
2
h-index
1
h-index
1
h-index
1–5 of 50
16
ASML (Netherlands)
Veldhoven, The Netherlands
3 h-index
6 publications
153 citations
ARC Centre of Excellence in Cognition and its Disorders
Sydney, Australia
1 h-index
2 publications
44 citations
University of California, Los Angeles
Los Angeles, United States
1 h-index
1 publications
24 citations
Intel (United States)
Santa Clara, United States
1 h-index
1 publications
11 citations
United States Department of Defense
Washington, United States
1 h-index
2 publications
34 citations
Carl Zeiss (Germany)
Oberkochen, Germany
1 h-index
7 publications
77 citations

Wuhan Institute of Technology
Wuhan, China
1 h-index
1 publications
39 citations
University of Tennessee at Knoxville
Knoxville, United States
1 h-index
1 publications
46 citations
1–8 of 16
3 publications · 38 citations
3
h-index
2 publications · 47 citations
3
h-index
SDI · 1 publications · 46 citations
1
h-index
1 publications · 17 citations
1
h-index
1 publications · 10 citations
1
h-index
1–5