1 code implementation • 17 Apr 2024 • George Retsinas, Giorgos Sfikas, Basilis Gatos, Christophoros Nikou
Handwritten text recognition has been developed rapidly in the recent years, following the rise of deep learning and its applications.
1 code implementation • 17 Apr 2024 • George Retsinas, Niki Efthymiou, Petros Maragos
We have validated the effectiveness of the proposed implicit-based approach for a synthetic test set, as well as provided qualitative results for a small set of real acquired point clouds with depth sensors.
no code implementations • 5 Apr 2024 • George Retsinas, Panagiotis P. Filntisis, Radek Danecek, Victoria F. Abrevaya, Anastasios Roussos, Timo Bolkart, Petros Maragos
Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image.
1 code implementation • 3 Oct 2023 • Athanasios Glentis Georgoulakis, George Retsinas, Petros Maragos
Neural Network pruning is an increasingly popular way for producing compact and efficient models, suitable for resource-limited environments, while preserving high performance.
no code implementations • 25 Sep 2023 • Ioannis Kordonis, Emmanouil Theodosis, George Retsinas, Petros Maragos
Matrix Factorization (MF) has found numerous applications in Machine Learning and Data Mining, including collaborative filtering recommendation systems, dimensionality reduction, data visualization, and community detection.
1 code implementation • 7 Aug 2023 • George Retsinas, Giorgos Sfikas, Christophoros Nikou
Recent advances in segmentation-free keyword spotting treat this problem w. r. t.
no code implementations • 4 Jul 2023 • Giorgos Sfikas, George Retsinas
We focus especially on the relation of Quaternion Fourier Transform matrices to Quaternion Circulant matrices (representing quaternionic convolution), and the eigenstructure of the latter.
1 code implementation • 29 Mar 2023 • Konstantina Nikolaidou, George Retsinas, Vincent Christlein, Mathias Seuret, Giorgos Sfikas, Elisa Barney Smith, Hamam Mokayed, Marcus Liwicki
Our proposed method is able to generate realistic word image samples from different writer styles, by using class index styles and text content prompts without the need of adversarial training, writer recognition, or text recognition.
Ranked #1 on HTR on IAM
1 code implementation • 22 Jul 2022 • Panagiotis P. Filntisis, George Retsinas, Foivos Paraperas-Papantoniou, Athanasios Katsamanis, Anastasios Roussos, Petros Maragos
The recent state of the art on monocular 3D face reconstruction from image data has made some impressive advancements, thanks to the advent of Deep Learning.
no code implementations • ICLR 2022 • Panagiotis Misiakos, Georgios Smyrnis, George Retsinas, Petros Maragos
Based on this result, we propose geometrical neural network compression methods that employ the K-means algorithm.
no code implementations • 29 Sep 2021 • George Retsinas, Giorgos Sfikas, Panagiotis Filntisis, Petros Maragos
Selecting an appropriate learning rate for efficiently training deep neural networks is a difficult process that can be affected by numerous parameters, such as the dataset, the model architecture or even the batch size.
no code implementations • 28 Dec 2020 • Vasiliki Tassopoulou, George Retsinas, Petros Maragos
In our work, we utilize a Multi-task Learning scheme, training the model to perform decompositions of the target sequence with target units of different granularity, from fine to coarse.
no code implementations • 17 Aug 2020 • George Retsinas, Giorgos Sfikas, Petros Maragos
The related joint loss leads to a boost in recognition performance, while the Seq2Seq branch is used to create efficient word representations.
1 code implementation • 4 Jun 2020 • George Retsinas, Athena Elafrou, Georgios Goumas, Petros Maragos
Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices.
no code implementations • CVPR 2019 • George Retsinas, Georgios Louloudis, Nikolaos Stamatopoulos, Giorgos Sfikas, Basilis Gatos
Three distinct components, all modeled as neural networks, are combined: normalization, feature extraction and representation of image and textual input into a common space.
no code implementations • 28 May 2019 • George Retsinas, Athena Elafrou, Georgios Goumas, Petros Maragos
In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs).