LogoDet-3K. A Large-scale Image Dataset for Logo Detection

doi:10.1145/3466780

	LogoDet-3K. A Large-scale Image Dataset for Logo Detection
	Wang, Jing 1; Min, Weiqing 2; Hou, Sujuan 1; Ma, Shengnan 1; Zheng, Yuanjie 1; Jiang, Shuqiang 2
	2022
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN	1551-6857
卷号	18 期号:1 页码:19
摘要	Logo detection has been gaining considerable attention because of its wide range of applications in the multimedia field, such as copyright infringement detection, brand visibility monitoring, and product brand management on social media. In this article, we introduce LogoDet-3K, the largest logo detection dataset with full annotation, which has 3,000 logo categories, about 200,000 manually annotated logo objects, and 158,652 images. LogoDet-3K creates a more challenging benchmark for logo detection, for its higher comprehensive coverage and wider variety in both logo categories and annotated objects compared with existing datasets. We describe the collection and annotation process of our dataset and analyze its scale and diversity in comparison to other datasets for logo detection. We further propose a strong baseline method Logo-Yolo, which incorporates Focal loss and Clot) loss into the basic YOLOv3 framework for large-scale logo detection. It obtains about 4% improvement on the average performance compared with YOLOv3, and greater improvements compared with reported several deep detection models on LogoDet-3K. We perform extensive evaluation on three other existing datasets to further verify on both logo detection and retrieval tasks, and we demonstrate better generalization ability of LogoDet-3K on logo detection and retrieval tasks. The LogoDet3K dataset is used to promote large-scale logo-related research. The code and LogoDet-3K can be found at https://github.com/Wangjing1551 /LogoDet-3K-Dataset.
关键词	Datasets logo detection multi-scale deep learning
DOI	10.1145/3466780
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62072289] ; National Natural Science Foundation of China[62073201] ; Postdoctoral Science Foundation of China[2017M612338] ; Shandong science and technology plan project[J17KB177]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:000772636900021
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：29[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18929
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Hou, Sujuan
作者单位	1.Shandong Normal Univ, Sch Informat Sci & Engn, 1 Daxue Rd, Jinan, Shandong, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, 6 Kexueyuan South Rd, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Wang, Jing,Min, Weiqing,Hou, Sujuan,et al. LogoDet-3K. A Large-scale Image Dataset for Logo Detection[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2022,18(1):19.
APA	Wang, Jing,Min, Weiqing,Hou, Sujuan,Ma, Shengnan,Zheng, Yuanjie,&Jiang, Shuqiang.(2022).LogoDet-3K. A Large-scale Image Dataset for Logo Detection.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,18(1),19.
MLA	Wang, Jing,et al."LogoDet-3K. A Large-scale Image Dataset for Logo Detection".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 18.1(2022):19.