output
20012026
most citedThe Cityscapes Dataset for Semantic Urban Scene Understanding

986 citations

Showing 2022Show all

10 papers · 1 filter

cs.CL2022★ 4 cited

Preserving Semantics in Textual Adversarial Attacks

David Herel, Hugo Cisneros, Tomas Mikolov

The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced e…

cond-mat.mes-hall2022★ 22 cited

Spin-orbit and exchange proximity couplings in graphene/1T-TaS heterostructure triggered by a charge density wave

Karol Szałowski, Marko Milivojević, Denis Kochan +1

Proximity-induced fine features and spin-textures of the electronic bands in graphene-based van der Waals heterostructures can be explored from the point of tailoring a twist angle…

cs.DS2022★ 2 cited

Faster parameterized algorithms for modification problems to minor-closed classes

Laure Morelle, Ignasi Sau, Giannos Stamoulis +1

Let be a minor-closed graph class and let be an -vertex graph. We say that is a -apex of if contains a set of at most vertices such…

cs.LG2022★ 1 cited

Benchmarking Learning Efficiency in Deep Reservoir Computing

Hugo Cisneros, Josef Sivic, Tomas Mikolov

It is common to evaluate the performance of a machine learning model by measuring its predictive power on a test dataset. This approach favors complicated models that can smoothly…

cs.RO2022★ 3 cited

Augmenting differentiable physics with randomized smoothing

Quentin Le Lidec, Louis Montaut, Cordelia Schmid +2

In the past few years, following the differentiable programming paradigm, there has been a growing interest in computing the gradient information of physical processes (e.g., physi…

cs.CV2022★ 64 cited

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Antoine Yang, Antoine Miech, Josef Sivic +2

Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious…

cs.CL2022★ 52 cited

FiNER: Financial Numeric Entity Recognition for XBRL Tagging

Lefteris Loukas, Manos Fergadiotis, Ilias Chalkidis +4

Publicly traded companies are required to submit periodic reports with eXtensive Business Reporting Language (XBRL) word-level tags. Manually tagging the reports is tedious and cos…

cs.AI2022★ 27 cited

"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks

Edoardo Mosca, Shreyash Agarwal, Javier Rando +1

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment…

cs.IT2022★ 1 cited

Information Decomposition Diagrams Applied beyond Shannon Entropy: A Generalization of Hu's Theorem

Leon Lang, Pierre Baudot, Rick Quax +1

In information theory, one major goal is to find useful functions that summarize the amount of information contained in the interaction of several random variables. Specifically, o…

cs.AI2022★ 65 cited

A Survey of Methods for Automated Algorithm Configuration

Elias Schede, Jasmin Brandt, Alexander Tornede +4

Algorithm configuration (AC) is concerned with the automated search of the most suitable parameter configuration of a parametrized algorithm. There is currently a wide variety of A…