Search Results for author: Ioannis Kompatsiaris

Found 22 papers, 12 papers with code

VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training

1 code implementation27 Jul 2022 Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Ioannis Kompatsiaris

For fashion outfits to be considered aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color.

Recommendation Systems

InDistill: Transferring Knowledge From Pruned Intermediate Layers

1 code implementation20 May 2022 Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Ioannis Kompatsiaris

The capacity gap between the models, the information encoding that collapses its architectural alignment, and the absence of appropriate learning schemes for transferring multiple layers restrict the performance of existing methods.

Knowledge Distillation

The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild

no code implementations27 Apr 2022 Spyridon Baxevanakis, Giorgos Kordopatis-Zilos, Panagiotis Galopoulos, Lazaros Apostolidis, Killian Levacher, Ipek B. Schlicht, Denis Teyssou, Ioannis Kompatsiaris, Symeon Papadopoulos

Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media.

DeepFake Detection Face Swapping

Multimodal Quasi-AutoRegression: Forecasting the visual popularity of new fashion products

no code implementations8 Apr 2022 Stefanos I. Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Ioannis Kompatsiaris

We employ the product's target attributes time series as a proxy of temporal popularity patterns, mitigating the lack of historical data, while exogenous time series help capture trends among interrelated attributes.

Image Captioning Image Classification +3

p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks

1 code implementation29 Nov 2021 Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris

In this work, we aim to classify nodes of unstructured peer-to-peer networks with communication uncertainty, such as users of decentralized social networks.

Node Classification

pygrank: A Python Package for Graph Node Ranking

1 code implementation18 Oct 2021 Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris, Andreas Symeonidis

We introduce pygrank, an open source Python package to define, run and evaluate node ranking algorithms.

A Survey on Bias in Visual Datasets

no code implementations16 Jul 2021 Simone Fabbrizzi, Symeon Papadopoulos, Eirini Ntoutsi, Ioannis Kompatsiaris

Hence, this work aims to: i) describe the biases that might manifest in visual datasets; ii) review the literature on methods for bias discovery and quantification in visual datasets; iii) discuss existing attempts to collect bias-aware visual datasets.

DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval

1 code implementation24 Jun 2021 Giorgos Kordopatis-Zilos, Christos Tzelepis, Symeon Papadopoulos, Ioannis Kompatsiaris, Ioannis Patras

In this work, we propose a Knowledge Distillation framework, called Distill-and-Select (DnS), that starting from a well-performing fine-grained Teacher Network learns: a) Student Networks at different retrieval performance and computational efficiency trade-offs and b) a Selector Network that at test time rapidly directs samples to the appropriate student to maintain both high retrieval performance and high computational efficiency.

Knowledge Distillation Video Retrieval

Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning

1 code implementation17 Oct 2020 Pavlos Avgoustinakis, Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Andreas L. Symeonidis, Ioannis Kompatsiaris

For the robust similarity calculation between two videos, we first extract representative audio-based video descriptors by leveraging transfer learning based on a Convolutional Neural Network (CNN) trained on a large scale dataset of audio events, and then we calculate the similarity matrix derived from the pairwise similarity of these descriptors.

Transfer Learning Video Retrieval

Investigating the Impact of Pre-processing and Prediction Aggregation on the DeepFake Detection Task

no code implementations12 Jun 2020 Polychronis Charitidis, Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Ioannis Kompatsiaris

In this paper, we propose a pre-processing step to improve the training data quality and examine its effect on the performance of DeepFake detection.

DeepFake Detection Face Swapping

MuSe 2020 -- The First International Multimodal Sentiment Analysis in Real-life Media Challenge and Workshop

1 code implementation30 Apr 2020 Lukas Stappen, Alice Baird, Georgios Rizos, Panagiotis Tzirakis, Xinchen Du, Felix Hafner, Lea Schumann, Adria Mallol-Ragolta, Björn W. Schuller, Iulia Lefter, Erik Cambria, Ioannis Kompatsiaris

Multimodal Sentiment Analysis in Real-life Media (MuSe) 2020 is a Challenge-based Workshop focusing on the tasks of sentiment recognition, as well as emotion-target engagement and trustworthiness detection by means of more comprehensively integrating the audio-visual and language modalities.

Emotion Recognition Multimodal Sentiment Analysis

ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning

1 code implementation ICCV 2019 Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Ioannis Patras, Ioannis Kompatsiaris

Subsequently, the similarity matrix between all video frames is fed to a four-layer CNN, and then summarized using Chamfer Similarity (CS) into a video-to-video similarity score -- this avoids feature aggregation before the similarity calculation between videos and captures the temporal similarity patterns between matching frame sequences.

Video Retrieval Video Similarity

FIVR: Fine-grained Incident Video Retrieval

1 code implementation11 Sep 2018 Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Ioannis Patras, Ioannis Kompatsiaris

To create the dataset, we devise a process for the collection of YouTube videos based on major news events from recent years crawled from Wikipedia and deploy a retrieval pipeline for the automatic selection of query videos based on their estimated suitability as benchmarks.

Video Retrieval

A Two-Level Classification Approach for Detecting Clickbait Posts using Text-Based Features

1 code implementation23 Oct 2017 Olga Papadopoulou, Markos Zampoglou, Symeon Papadopoulos, Ioannis Kompatsiaris

The detector is based almost exclusively on text-based features taken from previous work on clickbait detection, our own work on fake post detection, and features we designed specifically for the challenge.

Clickbait Detection Fake News Detection +1

The Dem@Care Experiments and Datasets: a Technical Report

no code implementations17 Dec 2016 Anastasios Karakostas, Alexia Briassouli, Konstantinos Avgerinakis, Ioannis Kompatsiaris, Magda Tsolaki

The objective of Dem@Care is the development of a complete system providing personal health services to people with dementia, as well as medical professionals and caregivers, by using a multitude of sensors, for context-aware, multi-parametric monitoring of lifestyle, ambient environment, and health parameters.

Decision Making

Comparative evaluation of state-of-the-art algorithms for SSVEP-based BCIs

3 code implementations2 Feb 2016 Vangelis P. Oikonomou, Georgios Liaros, Kostantinos Georgiadis, Elisavet Chatzilari, Katerina Adam, Spiros Nikolopoulos, Ioannis Kompatsiaris

Brain-computer interfaces (BCIs) have been gaining momentum in making human-computer interaction more natural, especially for people with neuro-muscular disabilities.


Monitoring Term Drift Based on Semantic Consistency in an Evolving Vector Field

1 code implementation5 Feb 2015 Peter Wittek, Sándor Darányi, Efstratios Kontopoulos, Theodoros Moysiadis, Ioannis Kompatsiaris

Based on the Aristotelian concept of potentiality vs. actuality allowing for the study of energy and dynamics in language, we propose a field approach to lexical analysis.

Lexical Analysis Philosophy

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