Related papers: CIUV: Collaborating Information Against Unreliable…
This paper focuses on a specific aspect of human visual discrimination from computationally generated solutions for CAAD ends. The bottleneck at work here concern informational ratios of discriminative rates over generative ones. The amount…
Fake news has become omnipresent in digitalized areas such as social media platforms. While being disseminated online, it also poses a threat to individuals and societies offline, for example, in the context of democratic elections.…
Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it. Despite rapid progress from triplet-trained compositors to zero-shot and generative methods, essentially all systems share one…
In this thesis, we address the challenging problem of unpaired multi-view clustering (UMC), which aims to achieve effective joint clustering using unpaired samples observed across multiple views. Traditional incomplete multi-view clustering…
Trustworthy multi-view classification (TMVC) addresses the challenge of achieving reliable decision-making in complex scenarios where multi-source information is heterogeneous, inconsistent, or even conflicting. Existing TMVC approaches…
How do news sources tackle controversial issues? In this work, we take a data-driven approach to understand how controversy interplays with emotional expression and biased language in the news. We begin by introducing a new dataset of…
Online IR tools have to take into account new phenomena linked to the appearance of blogs, wiki and other collaborative publications. Among these collaborative sites, Wikipedia represents a crucial source of information. However, the…
The proliferation of large language models (LLMs) has significantly advanced intelligent systems. Unfortunately, LLMs often face knowledge conflicts between internal memory and retrieved external information, arising from misinformation,…
Cyber threat intelligence (CTI) is essential for effective system defense. CTI is a collection of information about current or past threats to a computer system. This information is gathered by an agent through observation, or based on a…
Multi-view data are becoming common in real-world modeling tasks and many multi-view data clustering algorithms have thus been proposed. The existing algorithms usually focus on the cooperation of different views in the original space but…
As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human centric view governed by two principles:…
Suppose a decision maker wants to predict weather tomorrow by eliciting and aggregating information from crowd. How can the decision maker incentivize the crowds to report their information truthfully? Many truthful peer prediction…
Researchers have found that fake news spreads much times faster than real news. This is a major problem, especially in today's world where social media is the key source of news for many among the younger population. Fact verification,…
Information sharing on social media must be accompanied by attentive behavior so that in a distorted digital environment, users are not rushed and distracted in deciding to share information. The spread of misinformation, especially those…
We live in the Information Age, and information has become a critically important component of our life. The success of the Internet made huge amounts of it easily available and accessible to everyone. To keep the flow of this information…
Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models. HCCV datasets constructed through nonconsensual web scraping lack crucial metadata for…
The model of the attention economy, where content producers compete for the attention of users, relies on two key forces: information supply and demand. This study leverages the feedback loop between these forces to develop a method for…
Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. This…
Learning to Rank (LTR) from user interactions is challenging as user feedback often contains high levels of bias and noise. At the moment, two methodologies for dealing with bias prevail in the field of LTR: counterfactual methods that…
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReID is a challenging yet under-explored task. Most existing…