Recently, deep learning-based facial landmark detection has achieved significant
improvement. However, the semantic ambiguity problem degrades detection performance …

Cascaded computation, whereby predictions are recurrently refined over several stages, has
been a persistent theme throughout the development of landmark detection models. In this …

Multi-view finger-vein recognition technology has attracted increasing attentions in recent
years. Despite recent advances in the multi-view finger-vein identification, existing solutions …

Top-performing landmark estimation algorithms are based on exploiting the excellent ability
of large convolutional neural networks (CNNs) to represent local appearance. However, it is …

The field of fine-grained semantic segmentation for a person's face and head, which
includes identifying facial parts and head components, has made significant progress in …

Human tends to locate the facial landmarks with heavy occlusion by their relative position to
the easily identified landmarks. The clue is defined as the landmark inherent relation while it …

In this paper we address the challenge of making ViT models more robust to unseen affine
transformations. Such robustness becomes useful in various recognition tasks such as face …

The success of event camera (EC) vision in certain types of applications has been steadily
shown thanks to energy-efficient sparse sensing, high dynamic range, and extremely high …

Landmark detection under large pose with occlusion has been one of the challenging
problems in the field of facial analysis. Recently, many works have predicted pose or …

Facial landmark detection is an essential task in face-processing techniques. Traditional
methods, however, require expensive pixel-level labels. Semi-supervised facial landmark …