Search Results for author: Evgeny Krivosheev

Found 7 papers, 1 papers with code

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

1 code implementation CVPR 2021 Subhankar Roy, Evgeny Krivosheev, Zhun Zhong, Nicu Sebe, Elisa Ricci

In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains.

Curriculum Learning Domain Adaptation +1

Active Hybrid Classification

no code implementations21 Jan 2021 Evgeny Krivosheev, Fabio Casati, Alessandro Bozzon

Hybrid crowd-machine classifiers can achieve superior performance by combining the cost-effectiveness of automatic classification with the accuracy of human judgment.

Active Learning Classification +1

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

Siamese Graph Neural Networks for Data Integration

no code implementations17 Jan 2020 Evgeny Krivosheev, Mattia Atzeni, Katsiaryna Mirylenka, Paolo Scotton, Fabio Casati

In this work, we propose a general approach to modeling and integrating entities from structured data, such as relational databases, as well as unstructured sources, such as free text from news articles.

Combining Crowd and Machines for Multi-predicate Item Screening

no code implementations1 Apr 2019 Evgeny Krivosheev, Fabio Casati, Marcos Baez, Boualem Benatallah

This paper discusses how crowd and machine classifiers can be efficiently combined to screen items that satisfy a set of predicates.

Classification General Classification

Crowd-Machine Collaboration for Item Screening

no code implementations21 Mar 2018 Evgeny Krivosheev, Bahareh Harandizadeh, Fabio Casati, Boualem Benatallah

In this paper we describe how crowd and machine classifier can be efficiently combined to screen items that satisfy a set of predicates.

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