no code implementations • LTEDI (ACL) 2022 • Jetske Adams, Kyrill Poelmans, Iris Hendrickx, Martha Larson
This paper makes the case for studying concreteness in language as a bridge that will allow language technology to support the understanding and improvement of ethnic inclusivity in job advertisements.
no code implementations • EMNLP (Eval4NLP) 2020 • Klaus-Michael Lux, Maya Sappelli, Martha Larson
This paper presents a typology of errors produced by automatic summarization systems.
no code implementations • ACL (ECNLP) 2021 • Justine Winkler, Simon Brugman, Bas van Berkel, Martha Larson
We carry out a case study on the use of data programming to create data to train classifiers used for product moderation on a large e-commerce platform.
1 code implementation • 23 Mar 2024 • Mingliang Liang, Martha Larson
We introduce Gaussian masking for Language-Image Pre-Training (GLIP) a novel, straightforward, and effective technique for masking image patches during pre-training of a vision-language model.
no code implementations • 13 Nov 2023 • Bart Pleiter, Behrad Tajalli, Stefanos Koffas, Gorka Abad, Jing Xu, Martha Larson, Stjepan Picek
Our findings highlight the urgency of addressing such vulnerabilities and provide insights into potential countermeasures for securing DNN models against backdoors in tabular data.
no code implementations • 12 Oct 2023 • Manel Slokom, Peter-Paul de Wolf, Martha Larson
The attack assumes that the attacker can query the model to obtain predictions and that the marginal distribution of the data on which the model was trained is publicly available.
1 code implementation • 30 Jun 2023 • Loes Van Bemmel, Zhuoran Liu, Nik Vaessen, Martha Larson
Currently, the common practice for developing and testing gender protection algorithms is "neural-on-neural", i. e., perturbations are generated and tested with a neural network.
1 code implementation • 31 Jan 2023 • Zhuoran Liu, Zhengyu Zhao, Martha Larson
Perturbative availability poisons (PAPs) add small changes to images to prevent their use for model training.
1 code implementation • 2 Nov 2022 • Dirren van Vlijmen, Alex Kolmus, Zhuoran Liu, Zhengyu Zhao, Martha Larson
We introduce ShortcutGen, a new data poisoning attack that generates sample-dependent, error-minimizing perturbations by learning a generator.
no code implementations • 5 Aug 2022 • Danny Stax, Manel Slokom, Martha Larson
In this position paper, we make the case for applying the idea of minimal necessary data to recommender systems that use user reviews.
no code implementations • 28 Jul 2022 • Manel Slokom, Özlem Özgöbek, Martha Larson
This paper studies user attributes in light of current concerns in the recommender system community: diversity, coverage, calibration, and data minimization.
1 code implementation • 3 Jun 2022 • Zhengyu Zhao, Nga Dang, Martha Larson
In this paper, we propose that adversarial images should be evaluated based on semantic mismatch, rather than label mismatch, as used in current work.
no code implementations • LTEDI (ACL) 2022 • Anna Pillar, Kyrill Poelmans, Martha Larson
Deep learning holds great promise for detecting discriminatory language in the public sphere.
1 code implementation • 25 Nov 2021 • Zhuoran Liu, Zhengyu Zhao, Alex Kolmus, Tijn Berns, Twan van Laarhoven, Tom Heskes, Martha Larson
Recent work has shown that imperceptible perturbations can be applied to craft unlearnable examples (ULEs), i. e. images whose content cannot be used to improve a classifier during training.
no code implementations • 7 Oct 2021 • Manel Slokom, Martha Larson
We present a case that the newly emerging field of synthetic data in the area of recommender systems should prioritize `doing data right'.
4 code implementations • NeurIPS 2021 • Zhengyu Zhao, Zhuoran Liu, Martha Larson
In particular, we, for the first time, identify that a simple logit loss can yield competitive results with the state of the arts.
1 code implementation • 12 Nov 2020 • Zhengyu Zhao, Zhuoran Liu, Martha Larson
In particular, our color filter space is explicitly specified so that we are able to provide a systematic analysis of model robustness against adversarial color transformations, from both the attack and defense perspectives.
1 code implementation • 9 Aug 2020 • Manel Slokom, Martha Larson, Alan Hanjalic
This paper demonstrates the potential of statistical disclosure control for protecting the data used to train recommender systems.
1 code implementation • 2 Jun 2020 • Zhuoran Liu, Martha Larson
Our experiments evaluate the danger of these attacks when mounted against three representative visually-aware recommender algorithms in a framework that uses images to address cold start.
no code implementations • LREC 2020 • Nelleke Oostdijk, Hans van Halteren, Erkan Ba{\textcommabelow{s}}ar, Martha Larson
We carry out a manual analysis of 1000 articles containing a keyword related to flooding.
1 code implementation • 3 Feb 2020 • Zhengyu Zhao, Zhuoran Liu, Martha Larson
We introduce an approach that enhances images using a color filter in order to create adversarial effects, which fool neural networks into misclassification.
2 code implementations • CVPR 2020 • Zhengyu Zhao, Zhuoran Liu, Martha Larson
The success of image perturbations that are designed to fool image classifier is assessed in terms of both adversarial effect and visual imperceptibility.
no code implementations • 5 Sep 2019 • Xavier Bost, Serigne Gueye, Vincent Labatut, Martha Larson, Georges Linarès, Damien Malinas, Raphaël Roth
In this paper, we tackle plot modeling by considering the social network of interactions between the characters involved in the narrative: substantial, durable changes in a major character's social environment suggest a new development relevant for the summary.
1 code implementation • 29 Jan 2019 • Zhuoran Liu, Zhengyu Zhao, Martha Larson
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye.
1 code implementation • 23 Jul 2018 • Zhengyu Zhao, Martha Larson
As deep learning approaches to scene recognition emerge, they have continued to leverage discriminative regions at multiple scales, building on practices established by conventional image classification research.
no code implementations • 7 Jun 2018 • Emilia Gómez, Carlos Castillo, Vicky Charisi, Verónica Dahl, Gustavo Deco, Blagoj Delipetrev, Nicole Dewandre, Miguel Ángel González-Ballester, Fabien Gouyon, José Hernández-Orallo, Perfecto Herrera, Anders Jonsson, Ansgar Koene, Martha Larson, Ramón López de Mántaras, Bertin Martens, Marius Miron, Rubén Moreno-Bote, Nuria Oliver, Antonio Puertas Gallardo, Heike Schweitzer, Nuria Sebastian, Xavier Serra, Joan Serrà, Songül Tolan, Karina Vold
The workshop gathered an interdisciplinary group of experts to establish the state of the art research in the field and a list of future research challenges to be addressed on the topic of human and machine intelligence, algorithm's potential impact on human cognitive capabilities and decision making, and evaluation and regulation needs.
no code implementations • 13 Mar 2018 • Odette Scharenborg, Martha Larson
Music stretches with and without lyrics were sampled from the same song in order to control for factors beyond the presence of lyrics.
no code implementations • 12 Jan 2016 • Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic
The novelty of the approach is that subclass representations make use of not only the content of the photos themselves, but also information on the co-occurrence of their tags, which determines membership in both subclasses and top-level classes.
no code implementations • CVPR 2015 • Xinchao Li, Martha Larson, Alan Hanjalic
Spatial verification is a key step in boosting the performance of object-based image retrieval.
no code implementations • 20 Feb 2013 • Yue Shi, Martha Larson, Alan Hanjalic
A key question to be answered in the context of CDCF is what common characteristics can be deployed to link different domains for effective knowledge transfer.
no code implementations • LREC 2012 • Maria Eskevich, Gareth J. F. Jones, Martha Larson, Roel Ordelman,
We describe the development of a test collection for the investigation of speech retrieval beyond identification of relevant content.