Search Results for author: Ilias Papastratis

Found 5 papers, 2 papers with code

Multi-manifold Attention for Vision Transformers

no code implementations18 Jul 2022 DIMITRIOS KONSTANTINIDIS, Ilias Papastratis, Kosmas Dimitropoulos, Petros Daras

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition.

 Ranked #1 on Image Classification on Tiny-ImageNet (Top-1 Accuracy metric)

Action Recognition Classification +2

Ablation study of self-supervised learning for image classification

1 code implementation arXiv 2021 Ilias Papastratis

This project focuses on the self-supervised training of convolutional neural networks (CNNs) and transformer networks for the task of image recognition.

Classification Image Classification +1

Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network

no code implementations Sensors 2021 Ilias Papastratis, Kosmas Dimitropoulos, Petros Daras

The proposed network architecture consists of a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator’s predictions by modeling text information at the sentence and gloss levels.

Generative Adversarial Network Sentence +2

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