10 citations · 13 across the 3 of their papers we have counts for
3 papers
cs.CV2023
Read, look and detect: Bounding box annotation from image-caption pairs
Eduardo Hugo Sanchez
Various methods have been proposed to detect objects while reducing the cost of data annotation. For instance, weakly supervised object detection (WSOD) methods rely only on image-…
stat.ML2019★ 10 cited
Learning Disentangled Representations via Mutual Information Estimation
Eduardo Hugo Sanchez, Mathieu Serrurier, Mathias Ortner
In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representatio…
cs.CV2019★ 3 cited
Learning Disentangled Representations of Satellite Image Time Series
Eduardo Sanchez, Mathieu Serrurier, Mathias Ortner
In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data. Additio…