Capsule network with its limitation, modification, and applications—A survey

MU Haq, MAJ Sethi, AU Rehman - Machine Learning and Knowledge …, 2023 - mdpi.com
Numerous advancements in various fields, including pattern recognition and image
classification, have been made thanks to modern computer vision and machine learning …

A review of generative and non-generative adversarial attack on context-rich images

H Stanly, R Paul - Engineering Applications of Artificial Intelligence, 2023 - Elsevier
In this fast-moving digital era, millions of images are added to repositories every millisecond.
These images are context-rich images with ample underlying data that are extracted and …

Real-time driver monitoring system with facial landmark-based eye closure detection and head pose recognition

D Kim, H Park, T Kim, W Kim, J Paik - Scientific reports, 2023 - nature.com
This paper introduces a real-time Driver Monitoring System (DMS) designed to monitor
driver behavior while driving, employing facial landmark estimation-based behavior …

RobCaps: evaluating the robustness of capsule networks against affine transformations and adversarial attacks

A Marchisio, A De Marco, A Colucci… - … Joint Conference on …, 2023 - ieeexplore.ieee.org
Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships
between multiple objects for image classification tasks. Other than achieving high accuracy …

[PDF][PDF] CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features.

M Ul Haq, MAJ Sethi, N Ben Aoun… - … , Materials & Continua, 2024 - researchgate.net
Face recognition (FR) technology has numerous applications in artificial intelligence
including biometrics, security, authentication, law enforcement, and surveillance. Deep …

Adversarial Attacks and Defenses in Capsule Networks: A Critical Review of Robustness Challenges and Mitigation Strategies

M Shah, K Gandhi, S Joshi, MD Nagar, V Patel… - … on Advanced Computing …, 2023 - Springer
Abstract Capsule Networks (CapsNets) have gained significant attention in recent years due
to their potential for improved representation learning and robustness. However, their …