arXiv subjects

Ioannis Kompatsiaris

Publications and source records attributed to Ioannis Kompatsiaris.

49 records · Page 3Linked to original sources

arXiv2020

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

Recent advances in content generation technologies (widely known as DeepFakes) along with the online proliferation of manipulated media content render the detection of such manipulations a task of increasing importance. Even though there are many DeepFake detection methods, only a few focus on the impact of dataset preprocessing and the aggregation of frame-level to video-level prediction on model performance. 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. We also propose and evaluate the effect of video-level prediction aggregation approaches. Experimental results show that the proposed pre-processing approach leads to considerable improvements in the performance of detection models, and the proposed prediction aggregation scheme further boosts the detection efficiency in cases where there are multiple faces in a video.

cs.CV↗

arXiv2020

LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting

Multivariate time series forecasting is of great importance to many scientific disciplines and industrial sectors. The evolution of a multivariate time series depends on the dynamics of its variables and the connectivity network of causal interrelationships among them. Most of the existing time series models do not account for the causal effects among the system's variables and even if they do they rely just on determining the between-variables causality network. Knowing the structure of such a complex network and even more specifically knowing the exact lagged variables that contribute to the underlying process is crucial for the task of multivariate time series forecasting. The latter is a rather unexplored source of information to leverage. In this direction, here a novel neural network-based architecture is proposed, termed LAgged VAriable Representation NETwork (LAVARNET), which intrinsically estimates the importance of lagged variables and combines high dimensional latent representations of them to predict future values of time series. Our model is compared with other baseline and state of the art neural network architectures on one simulated data set and four real data sets from meteorology, music, solar activity, and finance areas. The proposed architecture outperforms the competitive architectures in most of the experiments.

cs.LG↗

arXiv2020

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

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. The purpose of MuSe 2020 is to bring together communities from different disciplines; mainly, the audio-visual emotion recognition community (signal-based), and the sentiment analysis community (symbol-based). We present three distinct sub-challenges: MuSe-Wild, which focuses on continuous emotion (arousal and valence) prediction; MuSe-Topic, in which participants recognise domain-specific topics as the target of 3-class (low, medium, high) emotions; and MuSe-Trust, in which the novel aspect of trustworthiness is to be predicted. In this paper, we provide detailed information on MuSe-CaR, the first of its kind in-the-wild database, which is utilised for the challenge, as well as the state-of-the-art features and modelling approaches applied. For each sub-challenge, a competitive baseline for participants is set; namely, on test we report for MuSe-Wild a combined (valence and arousal) CCC of .2568, for MuSe-Topic a score (computed as 0.34$\cdot$ UAR + 0.66$\cdot$F1) of 76.78 % on the 10-class topic and 40.64 % on the 3-class emotion prediction, and for MuSe-Trust a CCC of .4359.

cs.MM↗

arXiv2020

Towards Semantic Detection of Smells in Cloud Infrastructure Code

Automated deployment and management of Cloud applications relies on descriptions of their deployment topologies, often referred to as Infrastructure Code. As the complexity of applications and their deployment models increases, developers inadvertently introduce software smells to such code specifications, for instance, violations of good coding practices, modular structure, and more. This paper presents a knowledge-driven approach enabling developers to identify the aforementioned smells in deployment descriptions. We detect smells with SPARQL-based rules over pattern-based OWL 2 knowledge graphs capturing deployment models. We show the feasibility of our approach with a prototype and three case studies.

cs.SE↗

arXiv2020

Bias in Data-driven AI Systems -- An Introductory Survey

AI-based systems are widely employed nowadays to make decisions that have far-reaching impacts on individuals and society. Their decisions might affect everyone, everywhere and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multi-disciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well-grounded in a legal frame. In this survey, we focus on data-driven AI, as a large part of AI is powered nowadays by (big) data and powerful Machine Learning (ML) algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features like race, sex, etc.

cs.CY↗

arXiv2019

ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning

In this paper we introduce ViSiL, a Video Similarity Learning architecture that considers fine-grained Spatio-Temporal relations between pairs of videos -- such relations are typically lost in previous video retrieval approaches that embed the whole frame or even the whole video into a vector descriptor before the similarity estimation. By contrast, our Convolutional Neural Network (CNN)-based approach is trained to calculate video-to-video similarity from refined frame-to-frame similarity matrices, so as to consider both intra- and inter-frame relations. In the proposed method, pairwise frame similarity is estimated by applying Tensor Dot (TD) followed by Chamfer Similarity (CS) on regional CNN frame features - this avoids feature aggregation before the similarity calculation between frames. 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. We train the proposed network using a triplet loss scheme and evaluate it on five public benchmark datasets on four different video retrieval problems where we demonstrate large improvements in comparison to the state of the art. The implementation of ViSiL is publicly available.

cs.CV↗

arXiv2019

FIVR: Fine-grained Incident Video Retrieval

This paper introduces the problem of Fine-grained Incident Video Retrieval (FIVR). Given a query video, the objective is to retrieve all associated videos, considering several types of associations that range from duplicate videos to videos from the same incident. FIVR offers a single framework that contains several retrieval tasks as special cases. To address the benchmarking needs of all such tasks, we construct and present a large-scale annotated video dataset, which we call FIVR-200K, and it comprises 225,960 videos. 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. We also devise a protocol for the annotation of the dataset with respect to the four types of video associations defined by FIVR. Finally, we report the results of an experimental study on the dataset comparing five state-of-the-art methods developed based on a variety of visual descriptors, highlighting the challenges of the current problem.

cs.MM↗

arXiv2017

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

The emergence of social media as news sources has led to the rise of clickbait posts attempting to attract users to click on article links without informing them on the actual article content. This paper presents our efforts to create a clickbait detector inspired by fake news detection algorithms, and our submission to the Clickbait Challenge 2017. 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. We use a two-level classification approach, combining the outputs of 65 first-level classifiers in a second-level feature vector. We present our exploratory results with individual features and their combinations, taken from the post text and the target article title, as well as feature selection. While our own blind tests with the dataset led to an F-score of 0.63, our final evaluation in the Challenge only achieved an F-score of 0.43. We explore the possible causes of this, and lay out potential future steps to achieve more successful results.

cs.SI↗

arXiv2016

The Dem@Care Experiments and Datasets: a Technical Report

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. Multi-sensor data analysis, combined with intelligent decision making mechanisms, will allow an accurate representation of the person's current status and will provide the appropriate feedback, both to the person and the associated caregivers, enhancing the standard clinical workflow. Within the project framework, several data collection activities have taken place to assist technical development and evaluation tasks. In all these activities, particular attention has been paid to adhere to ethical guidelines and preserve the participants' privacy. This technical report describes shorty the (a) the main objectives of the project, (b) the main ethical principles and (c) the datasets that have been already created.

cs.CV↗

arXiv2016

Towards Air Quality Estimation Using Collected Multimodal Environmental Data

This paper presents an open platform, which collects multimodal environmental data related to air quality from several sources including official open sources, social media and citizens. Collecting and fusing different sources of air quality data into a unified air quality indicator is a highly challenging problem, leveraging recent advances in image analysis, open hardware, machine learning and data fusion and is expected to result in increased geographical coverage and temporal granularity of air quality data.

cs.CY↗

arXiv2016

A Generalised Differential Framework for Measuring Signal Sparsity

The notion of signal sparsity has been gaining increasing interest in information theory and signal processing communities. As a consequence, a plethora of sparsity metrics has been presented in the literature. The appropriateness of these metrics is typically evaluated against a set of objective criteria that has been proposed for assessing the credibility of any sparsity metric. In this paper, we propose a Generalised Differential Sparsity (GDS) framework for generating novel sparsity metrics whose functionality is based on the concept that sparsity is encoded in the differences among the signal coefficients. We rigorously prove that every metric generated using GDS satisfies all the aforementioned criteria and we provide a computationally efficient formula that makes GDS suitable for high-dimensional signals. The great advantage of GDS is its flexibility to offer sparsity metrics that can be well-tailored to certain requirements stemming from the nature of the data and the problem to be solved. This is in contrast to current state-of-the-art sparsity metrics like Gini Index (GI), which is actually proven to be only a specific instance of GDS, demonstrating the generalisation power of our framework. In verifying our claims, we have incorporated GDS in a stochastic signal recovery algorithm and experimentally investigated its efficacy in reconstructing randomly projected sparse signals. As a result, it is proven that GDS, in comparison to GI, both loosens the bounds of the assumed sparsity of the original signals and reduces the minimum number of projected dimensions, required to guarantee an almost perfect reconstruction of heavily compressed signals. The superiority of GDS over GI in conjunction with the fact that the latter is considered as a standard in numerous scientific domains, prove the great potential of GDS as a general purpose framework for measuring sparsity.

cs.IT↗

arXiv2016

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

Brain-computer interfaces (BCIs) have been gaining momentum in making human-computer interaction more natural, especially for people with neuro-muscular disabilities. Among the existing solutions the systems relying on electroencephalograms (EEG) occupy the most prominent place due to their non-invasiveness. However, the process of translating EEG signals into computer commands is far from trivial, since it requires the optimization of many different parameters that need to be tuned jointly. In this report, we focus on the category of EEG-based BCIs that rely on Steady-State-Visual-Evoked Potentials (SSVEPs) and perform a comparative evaluation of the most promising algorithms existing in the literature. More specifically, we define a set of algorithms for each of the various different parameters composing a BCI system (i.e. filtering, artifact removal, feature extraction, feature selection and classification) and study each parameter independently by keeping all other parameters fixed. The results obtained from this evaluation process are provided together with a dataset consisting of the 256-channel, EEG signals of 11 subjects, as well as a processing toolbox for reproducing the results and supporting further experimentation. In this way, we manage to make available for the community a state-of-the-art baseline for SSVEP-based BCIs that can be used as a basis for introducing novel methods and approaches.

cs.HC↗

arXiv2015

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

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. Falling back on the distributional hypothesis to statistically model word meaning, we used evolving fields as a metaphor to express time-dependent changes in a vector space model by a combination of random indexing and evolving self-organizing maps (ESOM). To monitor semantic drifts within the observation period, an experiment was carried out on the term space of a collection of 12.8 million Amazon book reviews. For evaluation, the semantic consistency of ESOM term clusters was compared with their respective neighbourhoods in WordNet, and contrasted with distances among term vectors by random indexing. We found that at 0.05 level of significance, the terms in the clusters showed a high level of semantic consistency. Tracking the drift of distributional patterns in the term space across time periods, we found that consistency decreased, but not at a statistically significant level. Our method is highly scalable, with interpretations in philosophy.

cs.CL↗