Semantic hierarchies for image annotation: A survey

By Anne-Marie Tousch, Stéphane Herbin, Jean-Yves Audibert. 2012

173 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

Recent advances in convolutional neural networks (2015, background): “Building a hierarchy of classifiers is a common strategy for image classification with a large number of classes [93].”
YOLO-based Object Detection Models: A Review and its Applications (2024, unknown): “In recent years, object detection has been a prominent task in CV (Computer Vision) [1] for reliable location and identification of objects within video or image.”
Large-Scale Object Classification Using Label Relation Graphs (2014, background): “Exploiting hierarchical structure of object categories has a long history [34].”
Explanatory Reasoning for Image Understanding Using Formal Concept Analysis and Description Logics (2014, unknown): “In most of these approaches, only the descriptive part of ontologies is used, as a common multilevel language to describe image content [23], or more recently as hierarchical semantic concept networks to refine image annotation [24] or to perform image classification [22], [25], [26].”
Blockout: Dynamic Model Selection for Hierarchical Deep Networks (2015, methodology): “Other methods for incorporating label structure are summarized in [24].”
Multi-label Learning with Missing Labels Using Mixed Dependency Graphs (2018, background): “…have been explored in many previous works, such as (Sun et al. 2010; Bucak et al. 2011; Chen et al. 2013; Wu et al. 2013; Lin et al. 2013; Geng et al. 2008; Chang et al. 2016; Wu et al. 2016; Li et al. 2016) (missing labels) and (Tousch et al. 2012; Wu et al. 2017, 2018) (semantic hierarchy).”
Fine-Grained Image Classification by Exploring Bipartite-Graph Labels (2015, background): “In the past few years, extensive research has been devoted to learning a hierarchical structure over classes (see [51] for a survey).”
Re-id: Hunting Attributes in the Wild (2014, background): “This approach differs from most work on conventional recognition [33] where images are categorically and strongly annotated - or derived from a heavily curated source such as an eCommerce website selling a catalogued array of products.”