34 citations · 37 across the 3 of their papers we have counts for
10 papers
Towards Reusable Network Components by Learning Compatible Representations
Michael Gygli, Jasper Uijlings, Vittorio Ferrari
This paper proposes to make a first step towards compatible and hence reusable network components. Rather than training networks for different tasks independently, we adapt the tra…
Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections
Theodora Kontogianni, Michael Gygli, Jasper Uijlings +1
In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an…
Natural Vocabulary Emerges from Free-Form Annotations
Jordi Pont-Tuset, Michael Gygli, Vittorio Ferrari
We propose an approach for annotating object classes using free-form text written by undirected and untrained annotators. Free-form labeling is natural for annotators, they intuiti…
Efficient Object Annotation via Speaking and Pointing
Michael Gygli, Vittorio Ferrari
Deep neural networks deliver state-of-the-art visual recognition, but they rely on large datasets, which are time-consuming to annotate. These datasets are typically annotated in t…
Fast Object Class Labelling via Speech
Michael Gygli, Vittorio Ferrari
Object class labelling is the task of annotating images with labels on the presence or absence of objects from a given class vocabulary. Simply asking one yes/no question per class…
PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation
Ana García del Molino, Michael Gygli
Highlight detection models are typically trained to identify cues that make visual content appealing or interesting for the general public, with the objective of reducing a video t…