Towards Zero-Shot Interpretable Human Recognition: A 2D-3D Registration Framework

arXiv:2403.06658v1 Announce Type: new
Abstract: Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands in terms of learning data; 2) the difficulties in generalising between different domains; and 3) the lack of interpretability/explainability, with biometrics being of particular interest, as it is important to provide evidence able to be used for forensics/legal purposes (e.g., in courts). To …

abstract architectures art arxiv biometric cs.cv data deep learning domains framework however human kind large vision models recognition registration state terms type vision vision models zero-shot