Search Results for author:
Found 44 papers, 23 papers with code
Sum of Group Error Differences: A Critical Examination of Bias Evaluation in Biometric Verification and a Dual-Metric Measure
Biometric Verification (BV) systems often exhibit accuracy disparities across different demographic groups, leading to biases in BV applications.
Fusion Transformer with Object Mask Guidance for Image Forgery Analysis
In this work, we introduce OMG-Fuser, a fusion transformer-based network designed to extract information from various forensic signals to enable robust image forgery detection and localization.
Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection
The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information.
FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail.
RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection
Online misinformation is often multimodal in nature, i. e., it is caused by misleading associations between texts and accompanying images.
FairBranch: Fairness Conflict Correction on Task-group Branches for Fair Multi-Task Learning
The generalization capacity of Multi-Task Learning (MTL) becomes limited when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients, resulting in negative transfer and a reduction in MTL accuracy compared to single-task learning (STL).
Mitigating Viewer Impact from Disturbing Imagery using AI Filters: A User-Study
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 potentially mitigate the emotional impact of viewing such disturbing content.
Towards Fair Face Verification: An In-depth Analysis of Demographic Biases
This paper presents an in-depth analysis, with a particular emphasis on the intersectionality of these demographic factors.
The 2023 Video Similarity Dataset and Challenge
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").
VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias
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.
FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual information between the features extracted by the model and a protected attribute, without the use of attribute labels.
Ranked #1 on
HairColor/Bias-conflicting
on CelebA
Improving Synthetically Generated Image Detection in Cross-Concept Settings
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.
Investigation of ensemble methods for the detection of deepfake face manipulations
The recent wave of AI research has enabled a new brand of synthetic media, called deepfakes.
MemeFier: Dual-stage Modality Fusion for Image Meme Classification
Hate speech is a societal problem that has significantly grown through the Internet.
Self-Supervised Video Similarity Learning
We introduce S$^2$VS, a video similarity learning approach with self-supervision.
Ranked #1 on
Video Retrieval
on FIVR-200K
Graph Neural Network Surrogates of Fair Graph Filtering
Graph filters that transform prior node values to posterior scores via edge propagation often support graph mining tasks affecting humans, such as recommendation and ranking.
Synthetic Misinformers: Generating and Combating Multimodal Misinformation
To address this, we perform a comparative study on existing and new Synthetic Misinformers that involves (1) out-of-context (OOC) image-caption pairs, (2) cross-modal named entity inconsistency (NEI) as well as (3) hybrid approaches and we evaluate them against real-world misinformation; using the COSMOS benchmark.
Design-time Fashion Popularity Forecasting in VR Environments
To this end, we develop a computer vision pipeline fine tuned on fashion imagery in order to extract relevant visual features along with the category and attributes of the garment.
A Multi-Stream Fusion Network for Image Splicing Localization
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.
Leveraging Large-scale Multimedia Datasets to Refine Content Moderation Models
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.
MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection
In this paper, we introduce MINTIME, a video deepfake detection approach that captures spatial and temporal anomalies and handles instances of multiple people in the same video and variations in face sizes.
Ranked #1 on
Classification
on ForgeryNet
AdaCC: Cumulative Cost-Sensitive Boosting for Imbalanced Classification
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.
VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training
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.
MemeTector: Enforcing deep focus for meme detection
To this end, we propose a methodology, called Visual Part Utilization, that utilizes the visual part of image memes as instances of the regular image class and the initial image memes as instances of the image meme class to force the model to concentrate on the critical parts that characterize an image meme.
InDistill: Information flow-preserving knowledge distillation for model compression
In this paper we introduce InDistill, a model compression approach that combines knowledge distillation and channel pruning in a unified framework for the transfer of the critical information flow paths from a heavyweight teacher to a lightweight student.
The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
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.
Multimodal Quasi-AutoRegression: Forecasting the visual popularity of new fashion products
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.
Ranked #1 on
Popularity Forecasting
on SHIFT15M
p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks
In this work, we aim to classify nodes of unstructured peer-to-peer networks with communication uncertainty, such as users of decentralized social networks.
Leveraging Selective Prediction for Reliable Image Geolocation
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.
pygrank: A Python Package for Graph Node Ranking
We introduce pygrank, an open source Python package to define, run and evaluate node ranking algorithms.
A Survey on Bias in Visual Datasets
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
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.
Ranked #2 on
Video Retrieval
on FIVR-200K
Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation
In this paper, we address the problem of global-scale image geolocation, proposing a mixed classification-retrieval scheme.
Operation-wise Attention Network for Tampering Localization Fusion
In this work, we present a deep learning-based approach for image tampering localization fusion.
Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning
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.
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.
Investigating the Impact of Pre-processing and Prediction Aggregation on the DeepFake Detection Task
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.
ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning
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.
Ranked #5 on
Video Retrieval
on FIVR-200K
Brenda Starr at SemEval-2019 Task 4: Hyperpartisan News Detection
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
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.
TOTEMSS: Topic-based, Temporal Sentiment Summarisation for Twitter
We present a system for time sensitive, topic based summarisation of the sentiment around target entities and topics in collections of tweets.
A Two-Level Classification Approach for Detecting Clickbait Posts using Text-Based Features
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.
A Physical Metaphor to Study Semantic Drift
By using term distances as a measure of semantic relatedness vs. their PageRank values indicating social importance and applied as variable `term mass', gravitation as a metaphor to express changes in the semantic content of a vector field lends a new perspective for experimentation.
Bridge Bounding: A Local Approach for Efficient Community Discovery in Complex Networks
There are numerous techniques adopting a global perspective to the community detection problem, i. e. they operate on the complete network structure, thus being computationally expensive and hard to apply in a streaming manner.
Data Analysis, Statistics and Probability Physics and Society
