Search Results for author: Ioannis Kansizoglou

Found 4 papers, 3 papers with code

Do Neural Network Weights account for Classes Centers?

1 code implementation14 Apr 2021 Ioannis Kansizoglou, Loukas Bampis, Antonios Gasteratos

The exploitation of Deep Neural Networks (DNNs) as descriptors in feature learning challenges enjoys apparent popularity over the past few years.

HASeparator: Hyperplane-Assisted Softmax

no code implementations8 Aug 2020 Ioannis Kansizoglou, Nicholas Santavas, Loukas Bampis, Antonios Gasteratos

Efficient feature learning with Convolutional Neural Networks (CNNs) constitutes an increasingly imperative property since several challenging tasks of computer vision tend to require cascade schemes and modalities fusion.

Image Classification

Deep Feature Space: A Geometrical Perspective

1 code implementation30 Jun 2020 Ioannis Kansizoglou, Loukas Bampis, Antonios Gasteratos

One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images.

Descriptive Reinforcement Learning (RL)

Attention! A Lightweight 2D Hand Pose Estimation Approach

1 code implementation22 Jan 2020 Nicholas Santavas, Ioannis Kansizoglou, Loukas Bampis, Evangelos Karakasis, Antonios Gasteratos

Vision based human pose estimation is an non-invasive technology for Human-Computer Interaction (HCI).

Hand Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.