Symeon Papadopoulos

The Centre for Research and Technology, Hellas · Information Technologies Institute (ITI)

Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model pruning, quantization, and hardware optimization, have made significant strides in this direction. However, t...

Recent works have established that AI models introduce spectral artifacts into generated images and propose approaches for learning to capture them using labeled data. However, the significant differences in such artifacts among different generative models hinder these approaches from generalizing to generators not seen during training. In this wor...

Deepfake technology has rapidly advanced, posing significant threats to information integrity and societal trust. While significant progress has been made in detecting deepfakes, the simultaneous manipulation of audio and visual modalities, sometimes at small parts but still altering the meaning, presents a more challenging detection scenario. We p...

Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using such data. However, most of them heavily rely on the availability of protected attribute labels in the datase...

Memes are an increasingly prevalent element of online discourse in social networks, especially among young audiences. They carry ideas and messages that range from humorous to hateful, and are widely consumed. Their potentially high impact requires adequate means of control to moderate their use in large scale. In this work, we propose SimCLIP a de...

Internet memes are a special type of digital content that is shared through social media. They have recently emerged as a popular new format of media communication. They are often multimodal, combining text with images and aim to express humor, irony, sarcasm, or sometimes convey hatred and misinformation. Automatically detecting memes is important...

Synthetic images disseminated online significantly differ from those used during the training and evaluation of the state-of-the-art detectors. In this work, we analyze the performance of synthetic image detectors as deceptive synthetic images evolve throughout their online lifespan. Our study reveals that, despite advancements in the field, curren...

Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations, they fail in complex real-world scenarios. In particular, existing methods excel in controlled experiments involving benchmarks with single-attribute injected biases, but...

Generative AI technologies produce hyper-realistic imagery that can be used for nefarious purposes such as producing misleading or harmful content, among others. This makes Synthetic Image Detection (SID) an essential tool for defending against AI-generated harmful content. Current SID methods typically resize input images to a fixed resolution or...

Out-of-context (OOC) misinformation poses a significant challenge in multimodal fact-checking, where images are paired with texts that misrepresent their original context to support false narratives. Recent research in evidence-based OOC detection has seen a trend towards increasingly complex architectures, incorporating Transformers, foundation mo...

Artificial intelligence systems often address fairness concerns by evaluating and mitigating measures of group discrimination, for example that indicate biases against certain genders or races. However, what constitutes group fairness depends on who is asked and the social context, whereas definitions are often relaxed to accept small deviations fr...

Simple Summary Digital health technologies can help manage the growing cancer burden, but understanding patients’ needs is crucial for these tools to be effective. Our study reviewed existing research on what cancer patients want from digital health technologies. We analysed 128 studies, focusing on web-based platforms, mobile apps, and wearable de...

Creating fair AI systems is a complex problem that involves the assessment of context-dependent bias concerns. Existing research and programming libraries express specific concerns as measures of bias that they aim to constrain or mitigate. In practice, one should explore a wide variety of (sometimes incompatible) measures before deciding which one...

AI systems rely on extensive training on large datasets to address various tasks. However, image-based systems, particularly those used for demographic attribute prediction, face significant challenges. Many current face image datasets primarily focus on demographic factors such as age, gender, and skin tone, overlooking other crucial facial attrib...

Being able to express broad families of equivariant or invariant attributed graph functions is a popular measuring stick of whether graph neural networks should be employed in practical applications. However, it is equally important to find deep local minima of losses (i.e., produce outputs with much smaller loss values compared to other minima), e...

Being able to express broad families of equivariant or invariant attributed graph functions is a popular measuring stick of whether graph neural networks should be employed in practical applications. However, it is equally important to learn deep local minima of losses (i.e., with much smaller loss values than other minima), even when architectures...

This article presents FRCSyn-onGoing, an ongoing challenge for face recognition where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases and standard experimental protocols. FRCSyn-onGoing is based on the Face Recognition Challenge in the Era of Synthetic Data (F...

Multimedia content has become ubiquitous on social media platforms, leading to the rise of multimodal misinformation (MM) and the urgent need for effective strategies to detect and prevent its spread. In recent years, the challenge of multimodal misinformation detection (MMD) has garnered significant attention by researchers and has mainly involved...

The Transformer, a neural network architecture, revolutionized Natural Language Processing and Computer Vision by effectively capturing contextual relationships in sequential data through its attention mechanism. While Transformers have been explored sufficiently in traditional computer vision tasks such as image classification, their application t...

Communication via digital means, such as mobile messaging applications (apps), plays an increasingly important role in everyday life. However, most messaging apps employ centralized computing principles that relinquish control of their users’ personal data to social network platform providers. Decentralization has been proposed as an alternative th...

Computer vision systems are employed in a variety of high-impact applications. However, making them trustworthy requires methods for the detection of potential biases in their training data, before models learn to harm already disadvantaged groups in downstream applications. Image data are typically represented via extracted features, which can be...

Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cloud-based solutions, have been found to exhibit significant biases related to race, age, and gender, a problem that requires in-depth exploration and solutions. This pape...

Exposure to disturbing imagery can significantly impact individuals, especially professionals who encounter such content as part of their work. This paper presents a user study, involving 107 participants, predominantly journalists and human rights investigators, that explores the capability of Artificial Intelligence (AI)-based image filters to po...

This work introduces a dataset, benchmark, and challenge for the problem of video copy detection and localization. The problem comprises two distinct but related tasks: determining whether a query video shares content with a reference video ("detection"), and additionally temporally localizing the shared content within each video ("localization")....

Image memes and specifically their widely known variation image macros are a special new media type that combines text with images and are used in social media to playfully or subtly express humor, irony, sarcasm and even hate. It is important to accurately retrieve image memes from social media to better capture the cultural and social aspects of...

New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and speed. In this paper, we focus on the challenge of generalizing across different concept classes, e.g., when tra...

The recent wave of AI research has enabled a new brand of synthetic media, called deepfakes. Deepfakes have impressive photorealism, which has generated exciting new use cases but also raised serious threats to our increasingly digital world. To mitigate these threats, researchers have tried to come up with new methods for deepfake detection that a...

Hate speech is a societal problem that has significantly grown through the Internet. New forms of digital content such as image memes have given rise to spread of hate using multimodal means, being far more difficult to analyse and detect compared to the unimodal case. Accurate automatic processing, analysis and understanding of this kind of conten...

We introduce S$^2$VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning. Here, in contrast to prior work, SSL is used to perform video similarity learning and address multiple retriev...

In this paper, we address the problem of image splicing localization with a multi-stream network architecture that processes the raw RGB image in parallel with other handcrafted forensic signals. Unlike previous methods that either use only the RGB images or stack several signals in a channel-wise manner, we propose an encoder-decoder architecture...

With the expansion of social media and the increasing dissemination of multimedia content, the spread of misinformation has become a major concern. This necessitates effective strategies for multimodal misinformation detection (MMD) that detect whether the combination of an image and its accompanying text could mislead or misinform. Due to the data...

A recurring graph analysis task is to rank nodes based on their relevance to overlapping communities of shared metadata attributes (e.g. the interests of social network users). To achieve this, approaches often start with a few example community members and employ graph filters that rank nodes based on their structural proximity to the examples. Ch...

Being able to forecast the popularity of new garment designs is very important in an industry as fast paced as fashion, both in terms of profitability and reducing the problem of unsold inventory. Here, we attempt to address this task in order to provide informative forecasts to fashion designers within a virtual reality designer application that w...

In this paper, we address the problem of image splicing localization with a multi-stream network architecture that processes the raw RGB image in parallel with other handcrafted forensic signals. Unlike previous methods that either use only the RGB images or stack several signals in a channel-wise manner, we propose an encoder-decoder architecture...

We introduce pygrank, an open source Python package to define, run and evaluate node ranking algorithms. We provide object-oriented and extensively unit-tested algorithmic components, such as graph filters, post-processors, measures, benchmarks, and online tuning. Computations can be delegated to numpy, tensorflow, or pytorch backends and fit in ba...

The sheer volume of online user-generated content has rendered content moderation technologies essential in order to protect digital platform audiences from content that may cause anxiety, worry, or concern. Despite the efforts towards developing automated solutions to tackle this problem, creating accurate models remains challenging due to the lac...

The overwhelming amount of information and misinformation on social media platforms has created a new role that these platforms are inclined to take on, that of the Internet custodian. Mainstream platforms, such as Facebook, Twitter and YouTube, are under tremendous public and political pressure to combat disinformation and remove harmful content....

Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating the classes differently, formulated typically via a user-defined fixed misclassification cost matrix provided...

Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend detection in fashion is a challenging task due to the fast pace of change in the fashion industry. Moreover, forecasting the visual popularity of new garment designs is eve...

Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating the classes differently, formulated typically via a user-defined fixed misclassification cost matrix provided...

In this paper, we discuss how we can re-imagine the interaction between users (i.e. fashion designers and consumers) and fashion items, by researching and developing technologies that allow virtual try-on of garments. In this direction we a) generate personal 3D avatars of the user, b) automatically simulate the interaction between 3D user avatars...

Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on training datasets and can learn and amplify biases that such datasets may carry. Thus, the problem of understanding and discovering bias in visua...

In order to consider fashion outfits as aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color. With the advent and omnipresence of computer vision deep learning models, increased interest has also emerged for the task of visual compatibility detection with the a...