Article-Journal

Multi-Task Explainable Quality Networks for Large-Scale Forensic Facial Recognition
Cite DOI URL
Direct multi-view spectral clustering with consistent kernelized graph and convolved nonnegative representation
Multi-view clustering attempts to partition unlabeled objects into clusters by making full use of complementary and consistent …
Cite Project DOI
Object-centric Contour-aware Data Augmentation Using Superpixels of Varying Granularity
Regional dropout strategies have demonstrated to be very effective in improving both the performance and the generalization capability …
Cite DOI URL
Inductive multi-view semi-supervised learning with a consensus graph
Graphs have a crucial impact on the performance of any graph-based semi-supervised learning method, so their construction should be …
Cite DOI URL
Joint graph and reduced flexible manifold embedding for scalable semi-supervised learning
Recently, graph-based semi-supervised learning (GSSL) has received much attention. On the other hand, less attention has been paid to …
Cite DOI URL
Folded: A toolkit to describe mammalian herbivore dentition from 2D images
Cite DOI
SuperpixelGridMasks data augmentation: Application to precision health and other real-world data
A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks …
Cite Code DOI URL
A unified deep semi-supervised graph learning scheme based on nodes re-weighting and manifold regularization
In recent years, semi-supervised learning on graphs has gained importance in many fields and applications. The goal is to use both …
Cite Project DOI URL
A deep learning loss based on additive cosine margin: Application to fashion style and face recognition
Recently, loss functions based on angular spans improved the performance of deep visual recognition. These losses converted Euclidean …
Cite DOI URL
Leveraging Synthetic Data for DNN-Based Visual Analysis of Passenger Seats
Cite DOI URL