Anomaly Detection and Open Set Recognition Applications for Computer Vision Call for Papers

IET Computer Vision Special Issue on 
Anomaly Detection and Open Set Recognition Applications for Computer Vision

Anomaly detection is a technique used to identify data points or
patterns that deviate significantly from the expected or normal
behaviour within a dataset. The goal is to flag observations that are
considered unusual, erroneous, anomalous, rare, or potentially
indicative of fraudulent or malicious activity. Open set recognition,
also known as open set identification or open set classification, is a
type of pattern recognition task that extends traditional
classification by considering the presence of unknown or novel classes
during the testing phase. From this point of view, there is a close
connection between anomaly detection and open set recognition as both
techniques target to detect samples coming from the unknown classes
and/or distributions. Open set recognition methods often involve
modelling - both known and unknown classes - during training,
capturing the distribution of known classes while explicitly modelling
the space of unknown classes. Open set recognition may involve
techniques such as using outlier detection, density estimation, or
modelling the decision boundaries in a way that allows for better
separation between known and unknown classes. This special issue
invites original contributions in introduction of novel datasets,
innovative architectures, and training methods for both visual anomaly
detection and open set recognition tasks.

Submission Deadline: 31st October 2023
Publication Date: April 2024

More information: https://ietresearch.onlinelibrary.wiley.com/hub/journal/17519640/homepage/call-for-papers/si-2023-000634