Weakly-Supervised Learning of Visual Relations

This paper introduces a novel approach for modeling visual relations between pairs of objects. We call relation a triplet of the form (subject; predicate; object) where the predicate is typically a preposition (eg. 'under', 'in front of') or a verb ('hold', 'ride&#...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / IEEE International Conference on Computer Vision S. 5189 - 5198
Hauptverfasser: Peyre, Julia, Laptev, Ivan, Schmid, Cordelia, Sivic, Josef
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2017
Schlagworte:
Biological system modeling
Detectors
Dogs
Feature extraction
Training
Visualization
ISSN:2380-7504
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper introduces a novel approach for modeling visual relations between pairs of objects. We call relation a triplet of the form (subject; predicate; object) where the predicate is typically a preposition (eg. 'under', 'in front of') or a verb ('hold', 'ride') that links a pair of objects (subject; object). Learning such relations is challenging as the objects have different spatial configurations and appearances depending on the relation in which they occur. Another major challenge comes from the difficulty to get annotations, especially at box-level, for all possible triplets, which makes both learning and evaluation difficult. The contributions of this paper are threefold. First, we design strong yet flexible visual features that encode the appearance and spatial configuration for pairs of objects. Second, we propose a weakly-supervised discriminative clustering model to learn relations from image-level labels only. Third we introduce a new challenging dataset of unusual relations (UnRel) together with an exhaustive annotation, that enables accurate evaluation of visual relation retrieval. We show experimentally that our model results in state-of-the-art results on the visual relationship dataset [32] significantly improving performance on previously unseen relations (zero-shot learning), and confirm this observation on our newly introduced UnRel dataset.
ISSN:2380-7504
DOI:10.1109/ICCV.2017.554