Search Results for author: Zoltán Szlávik

Found 4 papers, 0 papers with code

Towards Contrastive Learning in Music Video Domain

no code implementations1 Sep 2023 Karel Veldkamp, Mariya Hendriksen, Zoltán Szlávik, Alexander Keijser

To gain a better understanding of the reasons contrastive learning was not successful for music videos, we perform a qualitative analysis of the learned representations, revealing why contrastive learning might have difficulties uniting embeddings from two modalities.

Contrastive Learning Genre classification +3

Local Explanations for Clinical Search Engine results

no code implementations19 Oct 2021 Edeline Contempré, Zoltán Szlávik, Majid Mohammadi, Erick Velazquez, Annette ten Teije, Ilaria Tiddi

In this paper, a model-agnostic explainable method is developed to provide users with further information regarding the reasons why a clinical trial is retrieved in response to a query.

Disparate Impact Diminishes Consumer Trust Even for Advantaged Users

no code implementations29 Jan 2021 Tim Draws, Zoltán Szlávik, Benjamin Timmermans, Nava Tintarev, Kush R. Varshney, Michael Hind

Systems aiming to aid consumers in their decision-making (e. g., by implementing persuasive techniques) are more likely to be effective when consumers trust them.

Decision Making Fairness Human-Computer Interaction

Active Learning from Crowd in Document Screening

no code implementations11 Nov 2020 Evgeny Krivosheev, Burcu Sayin, Alessandro Bozzon, Zoltán Szlávik

In this paper, we explore how to efficiently combine crowdsourcing and machine intelligence for the problem of document screening, where we need to screen documents with a set of machine-learning filters.

Active Learning BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.