A survey of the vision transformers and their CNN-transformer based variants

A Khan, Z Rauf, A Sohail, AR Khan, H Asif… - Artificial Intelligence …, 2023 - Springer
Vision transformers have become popular as a possible substitute to convolutional neural
networks (CNNs) for a variety of computer vision applications. These transformers, with their …

Flexible Biometrics Recognition: Bridging the Multimodality Gap through Attention Alignment and Prompt Tuning

LCO Tiong, D Sigmund, CH Chan… - Proceedings of the …, 2024 - openaccess.thecvf.com
Periocular and face are complementary biometrics for identity management albeit with
inherent limitations notably in scenarios involving occlusion due to sunglasses or masks. In …

Local feature matching from detector-based to detector-free: a survey

Y Liao, Y Di, K Zhu, H Zhou, M Lu, Y Zhang, Q Duan… - Applied …, 2024 - Springer
Local feature matching has been a critical task in computer vision applications. In the early
days of computer vision, local feature matching relied heavily on detector-based methods …

Self-Attentive Contrastive Learning for Conditioned Periocular and Face Biometrics

TS Ng, JCL Chai, CY Low… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Periocular and face are two common biometric modalities for identity management.
Recently, the emergence of conditional biometrics has enabled the exploitation of the …

Low-resolution periocular images recognition using a novel CNN network

Q Zhou, Q Zou, X Gao, C Liu, C Feng… - Signal, Image and Video …, 2024 - Springer
In the context of the COVID-19 epidemic, periocular recognition has become a more
effective identity recognition way to replace face recognition. Although various identity …

Unmasking the imposters: towards improving the generalisation of deep learning methods for face presentation attack detection.

FC Abdullakutty - 2023 - rgu-repository.worktribe.com
Identity theft has had a detrimental impact on the reliability of face recognition, which has
been extensively employed in security applications. The most prevalent are presentation …