Weakly Supervised Anomaly Detection
Weakly Supervised Anomaly Detection is a method within the broader category of anomaly detection in time series that leverages partially labeled or coarsely annotated data to learn anomalous patterns, distinguishing itself from fully supervised and unsupervised approaches by relying on limited or imprecise label information for model training.
124
Publications
8.1K
Citations
377
Authors
162
Institutions
Publications per year
2017–2026
118
124
Anomaly Detection over Noisy Data Using Learned Probability Distributions
Eleazar Eskin · 2000 · 489 citations · Full text
1–5 of 124
377
6
h-index
Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates
5 publications · 396 citations
5
h-index
Electronics and Telecommunications Research Institute, South Korea
4 publications · 372 citations
4
h-index
4
h-index
3
h-index
1–5 of 377
162

Xidian University
Xi'an, China
7 h-index
20 publications
2.3K citations

Northwestern Polytechnical University
Xi'an, China
6 h-index
14 publications
1.2K citations
Tianjin University
Tianjin, China
5 h-index
14 publications
573 citations
Peng Cheng Laboratory
Shenzhen, China
5 h-index
9 publications
2.8K citations

Lawrence Berkeley National Laboratory
Berkeley, United States
4 h-index
7 publications
257 citations
Singapore Management University
Singapore, Singapore
4 h-index
4 publications
515 citations

The University of Adelaide
Adelaide, Australia
4 h-index
8 publications
2.8K citations
University of Chinese Academy of Sciences
Beijing, China
4 h-index
13 publications
1.1K citations
1–8 of 162
Repository · 6 publications · 152 citations
6
h-index
4 publications · 325 citations
5
h-index
2 publications · 66 citations
4
h-index
Conference · 4 publications · 679 citations
4
h-index
4 publications · 262 citations
4
h-index
1–5