Zero-shot Object Prediction using Semantic Scene Knowledge

Rene Grzeszick, Gernot A. Fink

2017

Abstract

This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scenarios with few or no annotated training samples. These scenarios are referred to as zero-shot or few-shot recognition and often build on visual attributes. Here, instead of relying on various visual attributes, a more direct way is pursued: after recognizing the scene that is depicted in an image, semantic relations between scenes and objects are used for predicting the presence of objects in an unsupervised manner. Most importantly, relations between scenes and objects can easily be obtained from external sources such as large scale text corpora from the web and, therefore, do not require tremendous manual labeling efforts. It will be shown that in cluttered scenes, where visual recognition is difficult, scene knowledge is an important cue for predicting objects.

Paper Citation

in Harvard Style

Grzeszick R. and Fink G. (2017). Zero-shot Object Prediction using Semantic Scene Knowledge . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 120-129. DOI: 10.5220/0006240901200129

in Bibtex Style

@conference{visapp17,
author={Rene Grzeszick and Gernot A. Fink},
title={Zero-shot Object Prediction using Semantic Scene Knowledge},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={120-129},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006240901200129},
isbn={978-989-758-226-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Zero-shot Object Prediction using Semantic Scene Knowledge
SN - 978-989-758-226-4
AU - Grzeszick R.
AU - Fink G.
PY - 2017
SP - 120
EP - 129
DO - 10.5220/0006240901200129