no code implementations • 6 Mar 2024 • Louis Mahon, Mirella Lapata
In this paper we address the task of summarizing television shows, which touches key areas in AI research: complex reasoning, multiple modalities, and long narratives.
no code implementations • 26 Jun 2023 • Louis Mahon, Thomas Lukasiewicz
We conduct experiments on seven different sets of images, which show that our method assigns the most accurate scores to all images considered.
no code implementations • 5 Apr 2023 • Louis Mahon, Lei Shah, Thomas Lukasiewicz
Recent years have seen growing interest in learning disentangled representations, in which distinct features, such as size or shape, are represented by distinct neurons.
1 code implementation • 29 Mar 2023 • Louis Mahon, Thomas Lukasiewicz
We propose a method that does not require data augmentation, and that, differently from existing methods, regularizes the hard assignments.
1 code implementation • Asian Conference on Machine Learning 2023 • Louis Mahon, Thomas Lukasiewicz
Progress is starting to be made in the unsupervised setting, in the form of deep HAR clustering models, which can assign labels to data without having been given any labels to train on, but there are problems with evaluating deep HAR clustering models, which makes assessing the field and devising new methods difficult.
Ranked #1 on Human Activity Recognition on PAMAP2
1 code implementation • 5 Mar 2022 • Louis Mahon, Carl Vogel
This paper presents FASTFOOD, a rule-based Natural Language Generation Program for cooking recipes.
2 code implementations • 22 Sep 2021 • Ida Szubert, Omri Abend, Nathan Schneider, Samuel Gibbon, Louis Mahon, Sharon Goldwater, Mark Steedman
We then demonstrate the utility of the compiled corpora through (1) a longitudinal corpus study of the prevalence of different syntactic and semantic phenomena in the CDS, and (2) applying an existing computational model of language acquisition to the two corpora and briefly comparing the results across languages.
1 code implementation • 22 Jul 2021 • Louis Mahon, Thomas Lukasiewicz
The most accurate existing approaches combine the training of the DNN with the clustering objective, so that information from the clustering process can be used to update the DNN to produce better features for clustering.
Ranked #1 on Image Clustering on USPS
1 code implementation • 20 Jul 2020 • Louis Mahon, Eleonora Giunchiglia, Bowen Li, Thomas Lukasiewicz
Nearly all existing techniques for automated video annotation (or captioning) describe videos using natural language sentences.