PP8K: A New Dataset for 8K UHD Video Compression and Processing

IF 2.3 4区计算机科学 Q2 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

IEEE MultiMedia Pub Date : 2023-07-01 DOI:10.1109/MMUL.2023.3269459

Wei Gao, Hang Yuan, Guibiao Liao, Zixuan Guo, Jianing Chen

{"title":"PP8K: A New Dataset for 8K UHD Video Compression and Processing","authors":"Wei Gao, Hang Yuan, Guibiao Liao, Zixuan Guo, Jianing Chen","doi":"10.1109/MMUL.2023.3269459","DOIUrl":null,"url":null,"abstract":"In the new era of ultra-high definition (UHD) videos, 8K is becoming more popular in diversified applications to boost the human visual experience and the performances of related vision tasks. However, researchers still suffer from the lack of 8K video sources to develop better processing algorithms for the compression, saliency detection, quality assessment, and vision analysis tasks. To ameliorate this situation, we construct a new comprehensive 8K UHD video dataset, which has two sub-datasets, i.e., the common raw format videos (CRFV) dataset and the video salient object detection (VSOD) dataset. To fully validate the diversity and practicality, the spatial and temporal information characteristics of the CRFV dataset are evaluated by the widely used metrics and the video encoder. Through the extensive experiments and comparative analyses with the other counterpart datasets, the proposed 8K dataset shows apparent advantages in diversity and practicality, which can benefit its applications for the developments of UHD video technologies. This dataset has been released online: https://git.openi.org.cn/OpenDatasets/PP8K.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"30 1","pages":"100-109"},"PeriodicalIF":2.3000,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE MultiMedia","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/MMUL.2023.3269459","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 2

Abstract

In the new era of ultra-high definition (UHD) videos, 8K is becoming more popular in diversified applications to boost the human visual experience and the performances of related vision tasks. However, researchers still suffer from the lack of 8K video sources to develop better processing algorithms for the compression, saliency detection, quality assessment, and vision analysis tasks. To ameliorate this situation, we construct a new comprehensive 8K UHD video dataset, which has two sub-datasets, i.e., the common raw format videos (CRFV) dataset and the video salient object detection (VSOD) dataset. To fully validate the diversity and practicality, the spatial and temporal information characteristics of the CRFV dataset are evaluated by the widely used metrics and the video encoder. Through the extensive experiments and comparative analyses with the other counterpart datasets, the proposed 8K dataset shows apparent advantages in diversity and practicality, which can benefit its applications for the developments of UHD video technologies. This dataset has been released online: https://git.openi.org.cn/OpenDatasets/PP8K.

查看原文本刊更多论文

PP8K:用于8K超高清视频压缩和处理的新数据集

在超高清视频的新时代，8K在多样化的应用中越来越受欢迎，以提升人类视觉体验和相关视觉任务的表现。然而，研究人员仍然缺乏8K视频源，无法为压缩、显著性检测、质量评估和视觉分析任务开发更好的处理算法。为了改善这种情况，我们构建了一个新的综合8K超高清视频数据集，该数据集有两个子数据集，即常见原始格式视频（CRFV）数据集和视频显著对象检测（VSOD）数据集。为了充分验证其多样性和实用性，通过广泛使用的度量和视频编码器来评估CRFV数据集的空间和时间信息特性。通过广泛的实验和与其他数据集的比较分析，所提出的8K数据集在多样性和实用性方面具有明显的优势，有利于其在超高清视频技术发展中的应用。此数据集已在线发布：https://git.openi.org.cn/OpenDatasets/PP8K.

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE MultiMedia 工程技术-计算机：理论方法

CiteScore

6.40

自引率

3.10%

发文量

审稿时长

>12 weeks

期刊介绍： The magazine contains technical information covering a broad range of issues in multimedia systems and applications. Articles discuss research as well as advanced practice in hardware/software and are expected to span the range from theory to working systems. Especially encouraged are papers discussing experiences with new or advanced systems and subsystems. To avoid unnecessary overlap with existing publications, acceptable papers must have a significant focus on aspects unique to multimedia systems and applications. These aspects are likely to be related to the special needs of multimedia information compared to other electronic data, for example, the size requirements of digital media and the importance of time in the representation of such media. The following list is not exhaustive, but is representative of the topics that are covered: Hardware and software for media compression, coding & processing; Media representations & standards for storage, editing, interchange, transmission & presentation; Hardware platforms supporting multimedia applications; Operating systems suitable for multimedia applications; Storage devices & technologies for multimedia information; Network technologies, protocols, architectures & delivery techniques intended for multimedia; Synchronization issues; Multimedia databases; Formalisms for multimedia information systems & applications; Programming paradigms & languages for multimedia; Multimedia user interfaces; Media creation integration editing & management; Creation & modification of multimedia applications.