48 citations · 125 across the 17 of their papers we have counts for
19 papers
Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classification
Aisha Zulfiqar, Ebroul Izquiedro
Plant species exhibit significant intra-class variation and minimal inter-class variation. To enhance classification accuracy, it is essential to reduce intra-class variation while…
Joint Neural Networks for One-shot Object Recognition and Detection
Camilo J. Vargas, Qianni Zhang, Ebroul Izquierdo
This paper presents a novel joint neural networks approach to address the challenging one-shot object recognition and detection tasks. Inspired by Siamese neural networks and state…
Efficient Convolution and Transformer-Based Network for Video Frame Interpolation
Issa Khalifeh, Luka Murn, Marta Mrak +1
Video frame interpolation is an increasingly important research task with several key industrial applications in the video coding, broadcast and production sectors. Recently, trans…
Multi-encoder Network for Parameter Reduction of a Kernel-based Interpolation Architecture
Issa Khalifeh, Marc Gorriz Blanch, Ebroul Izquierdo +1
Video frame interpolation involves the synthesis of new frames from existing ones. Convolutional neural networks (CNNs) have been at the forefront of the recent advances in this fi…
Complexity Reduction of Learned In-Loop Filtering in Video Coding
Woody Bayliss, Luka Murn, Ebroul Izquierdo +2
In video coding, in-loop filters are applied on reconstructed video frames to enhance their perceptual quality, before storing the frames for output. Conventional in-loop filters a…
SSDL: Self-Supervised Domain Learning for Improved Face Recognition
S. W. Arachchilage, E. Izquierdo
Face recognition in unconstrained environments is challenging due to variations in illumination, quality of sensing, motion blur and etc. An individual's face appearance can vary d…