Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective
This article takes a problem-oriented perspective and presents a comprehensive review of
transfer-learning methods, both shallow and deep, for cross-dataset visual recognition …
transfer-learning methods, both shallow and deep, for cross-dataset visual recognition …
A survey on heterogeneous face recognition: Sketch, infra-red, 3D and low-resolution
Heterogeneous face recognition (HFR) refers to matching face imagery across different
domains. It has received much interest from the research community as a result of its …
domains. It has received much interest from the research community as a result of its …
A comprehensive database for benchmarking imaging systems
Cross-modality face recognition is an emerging topic due to the wide-spread usage of
different sensors in day-to-day life applications. The development of face recognition …
different sensors in day-to-day life applications. The development of face recognition …
A survey on adversarial domain adaptation
M HassanPour Zonoozi, V Seydi - Neural Processing Letters, 2023 - Springer
Having a lot of labeled data is always a problem in machine learning issues. Even by
collecting lots of data hardly, shift in data distribution might emerge because of differences in …
collecting lots of data hardly, shift in data distribution might emerge because of differences in …
Heterogeneous face recognition with CNNs
Heterogeneous face recognition aims to recognize faces across different sensor modalities.
Typically, gallery images are normal visible spectrum images, and probe images are …
Typically, gallery images are normal visible spectrum images, and probe images are …
DLFace: Deep local descriptor for cross-modality face recognition
Cross-modality face recognition aims to identify faces across different modalities, such as
matching sketches with photos, low resolution face images with high resolution images, and …
matching sketches with photos, low resolution face images with high resolution images, and …
Composite sketch recognition via deep network-a transfer learning approach
Sketch recognition is one of the integral components used by law enforcement agencies in
solving crime. In recent past, software generated composite sketches are being preferred as …
solving crime. In recent past, software generated composite sketches are being preferred as …
Matching software-generated sketches to face photographs with a very deep CNN, morphed faces, and transfer learning
C Galea, RA Farrugia - IEEE Transactions on Information …, 2017 - ieeexplore.ieee.org
Sketches obtained from eyewitness descriptions of criminals have proven to be useful in
apprehending criminals, particularly when there is a lack of evidence. Automated methods to …
apprehending criminals, particularly when there is a lack of evidence. Automated methods to …
Integrating the digital twin concept into the evaluation of reconfigurable manufacturing systems (RMS): literature review and research trend
JK Touckia - The International Journal of Advanced Manufacturing …, 2023 - Springer
With the rapid advent of new information technologies (Big Data analytics, cyber-physical
systems, such as IoT, cloud computing and artificial intelligence), digital twins are being …
systems, such as IoT, cloud computing and artificial intelligence), digital twins are being …
Coupled attribute learning for heterogeneous face recognition
Heterogeneous face recognition (HFR) is a challenging problem in face recognition and
subject to large textural and spatial structure differences of face images. Different from …
subject to large textural and spatial structure differences of face images. Different from …