.png){kind=icon}
返回
Relation Regularized Scene Graph Generation
.png){kind=icon}
OA
AI
DOI：10.1109/TCYB.2021.3052522.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior knowledge, the performance of SGG is significantly improved. Inspired by this observation, in this article, we propose a relation regularized network (R2-Net), which can predict whether there is a relationship between two objects and encode this relation into object feature refinement and better SGG. Specifically, we first construct an affinity matrix among detected objects to represent the probability of a relationship between two objects. Graph convolution networks (GCNs) over this relation affinity matrix are then used as object encoders, producing relation-regularized representations of objects. With these relation-regularized features, our R2-Net can effectively refine object labels and generate scene graphs. Extensive experiments are conducted on the visual genome dataset for three SGG tasks (i.e., predicate classification, scene graph classification, and scene graph detection), demonstrating the effectiveness of our proposed method. Ablation studies also verify the key roles of our proposed components in performance improvement.
Keyword:
Visualization
Feature extraction
Task analysis
Semantics
Detectors
Proposals
Convolution
Graph convolution networks (GCNs)
scene graph generation (SGG)
visual relationship
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
Transcription initiation of distant core promoters in a large-sized genome of an insect.png)
BMC BiologyOAAI
BMC BiologyIF0
OAAI分享收藏分享收藏Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations视觉基因组: 使用众包密集图像注释连接语言和视觉OAAI
OAAI分享收藏分享收藏
查看更多内容