Related papers: A Taxonomy of Decentralized Identifier Methods for…
Self-supervised learning is a popular and powerful method for utilizing large amounts of unlabeled data, for which a wide variety of training objectives have been proposed in the literature. In this study, we perform a Bayesian analysis of…
Deep subspace clustering (DSC) algorithms face several challenges that hinder their widespread adoption across variois application domains. First, clustering quality is typically assessed using only the encoder's output layer, disregarding…
Gait recognition is an appealing biometric modality which aims to identify individuals based on the way they walk. Deep learning has reshaped the research landscape in this area since 2015 through the ability to automatically learn…
Task abstractions and taxonomic structures for tasks are useful for designers of interactive data analysis approaches, serving as design targets and evaluation criteria alike. For individual data types, dataset-specific taxonomic structures…
Due to the widespread COVID-19 pandemic, there has been a push for `immunity passports' and even technical proposals. Although the debate about the medical and ethical problems of immunity passports has been widespread, there has been less…
While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this…
Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing attention. Existing methods either design customized losses…
Unsupervised domain adaptation (UDA) methods for person re-identification (re-ID) aim at transferring re-ID knowledge from labeled source data to unlabeled target data. Although achieving great success, most of them only use limited data…
The passing of the eIDAS amendment marks an important milestone for EU countries and changes how they must manage digital credentials for both public services and businesses. Italy has led in adopting eIDAS, first with CIE and SPID identity…
We introduce a risk assessment framework for digital identification systems, as well as recommended best practices to enhance privacy, security, and other desirable properties in these systems. To generate these resources, we created a…
This paper discusses a practical approach that combines synthetic control with triple difference to address violations of the parallel trends assumption. By transforming triple difference into a DID structure, we can apply synthetic control…
In many applications, identity management (IdM) is used to associate a subject public key with an endpoint at which the subject can be contacted (telephone number, email, etc.). In decentralized applications based on distributed ledger…
Subspace identification (SID) has been widely used in system identification and control fields since it can estimate system models only relying on the input and output data by reliable numerical operations such as singular value…
We present the Deep Picard Iteration (DPI) method, a new deep learning approach for solving high-dimensional partial differential equations (PDEs). The core innovation of DPI lies in its use of Picard iteration to reformulate the typically…
Identifiers, such as method and variable names, form a large portion of source code. Therefore, low-quality identifiers can substantially hinder code comprehension. To support developers in using meaningful identifiers, several…
Dataset transparency is a key enabler of responsible AI, but insights into multimodal dataset attributes that impact trustworthy and ethical aspects of AI applications remain scarce and are difficult to compare across datasets. To address…
Explainability and evaluation of AI models are crucial parts of the security of modern intrusion detection systems (IDS) in the network security field, yet they are lacking. Accordingly, feature selection is essential for such parts in IDS…
Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…
Representing a space of handwriting stroke styles includes the challenge of representing both the style of each character and the overall style of the human writer. Existing VRNN approaches to representing handwriting often do not…
Ensuring the de-identification of medical imaging data is a critical step in enabling safe data sharing. This paper presents a hybrid de-identification framework designed to process Digital Imaging and Communications in Medicine (DICOM)…