Search Results for author: Giorgos Kordopatis-Zilos

Found 10 papers, 4 papers with code

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

Leveraging Selective Prediction for Reliable Image Geolocation

no code implementations23 Nov 2021 Apostolos Panagiotopoulos, Giorgos Kordopatis-Zilos, Symeon Papadopoulos

In this paper, we define the task of image localizability, i. e. suitability of an image for geolocation, and propose a selective prediction methodology to address the task.

Fake News Detection

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

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

Brenda Starr at SemEval-2019 Task 4: Hyperpartisan News Detection

no code implementations SEMEVAL 2019 Olga Papadopoulou, Giorgos Kordopatis-Zilos, Markos Zampoglou, Symeon Papadopoulos, Yiannis Kompatsiaris

In the effort to tackle the challenge of Hyperpartisan News Detection, i. e., the task of deciding whether a news article is biased towards one party, faction, cause, or person, we experimented with two systems: i) a standard supervised learning approach using superficial text and bag-of-words features from the article title and body, and ii) a deep learning system comprising a four-layer convolutional neural network and max-pooling layers after the embedding layer, feeding the consolidated features to a bi-directional recurrent neural network.

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

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