LogoDet-3K. A Large-scale Image Dataset for Logo Detection
文献类型:期刊论文
作者 | Wang, Jing2; Min, Weiqing1; Hou, Sujuan2; Ma, Shengnan2; Zheng, Yuanjie2; Jiang, Shuqiang1 |
刊名 | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS |
出版日期 | 2022 |
卷号 | 18期号:1页码:19 |
ISSN号 | 1551-6857 |
关键词 | Datasets logo detection multi-scale deep learning |
DOI | 10.1145/3466780 |
英文摘要 | 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. |
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 |
语种 | 英语 |
出版者 | ASSOC COMPUTING MACHINERY |
WOS记录号 | WOS:000772636900021 |
源URL | [http://119.78.100.204/handle/2XEOYT63/18928] |
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.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, 6 Kexueyuan South Rd, Beijing, Peoples R China 2.Shandong Normal Univ, Sch Informat Sci & Engn, 1 Daxue Rd, Jinan, Shandong, 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. |
入库方式: OAI收割
来源:计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。