Visual Relationship Detection: A Survey

Document Type

Article

Publication Date

8-1-2022

Abstract

Visual relationship detection (VRD) is one newly developed computer vision task, aiming to recognize relations or interactions between objects in an image. It is a further learning task after object recognition, and is important for fully understanding images even the visual world. It has numerous applications, such as image retrieval, machine vision in robotics, visual question answer (VQA), and visual reasoning. However, this problem is difficult since relationships are not definite, and the number of possible relations is much larger than objects. So the complete annotation for visual relationships is much more difficult, making this task hard to learn. Many approaches have been proposed to tackle this problem especially with the development of deep neural networks in recent years. In this survey, we first introduce the background of visual relations. Then, we present categorization and frameworks of deep learning models for visual relationship detection. The high-level applications, benchmark datasets, as well as empirical analysis are also introduced for comprehensive understanding of this task.

Identifier

85123781319 (Scopus)

Publication Title

IEEE Transactions on Cybernetics

External Full Text Location

https://doi.org/10.1109/TCYB.2022.3142013

e-ISSN

21682275

ISSN

21682267

PubMed ID

35077387

First Page

8453

Last Page

8466

Issue

8

Volume

52

This document is currently not available here.

Share

COinS