Rethinking Semantic Image Compression: Scalable Representation With Cross-Modality Transfer

doi:10.1109/TCSVT.2023.3241225

	Rethinking Semantic Image Compression: Scalable Representation With Cross-Modality Transfer
	Zhang, Pingping 1; Wang, Shiqi 1,2; Wang, Meng 1; Li, Jiguo 3; Wang, Xu 4,5; Kwong, Sam 1,2
	2023-08-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	33 期号:8 页码:4441-4445
摘要	This article proposes the scalable cross-modality compression (SCMC) paradigm, in which the image compression problem is further cast into a representation task by hierarchically sketching the image with different modalities. Herein, we adopt the conceptual organization philosophy to model the overwhelmingly complicated visual patterns, based upon the semantic, structure, and signal level representation accounting for different tasks. The SCMC paradigm that incorporates the representation at different granularities supports diverse application scenarios, such as high-level semantic communication and low-level image reconstruction. The decoder, which enables the recovery of the visual information, benefits from the scalable coding based upon the semantic, structure, and signal layers. Qualitative and quantitative results demonstrate that the SCMC can convey accurate semantic and perceptual information of images, especially at low bitrates, and promising rate-distortion performance has been achieved compared to state-of-the-art methods. The code will be available online https://github.com/ppingzhang/SCMC.
关键词	Semantic image compression cross-modality scalable coding
DOI	10.1109/TCSVT.2023.3241225
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62022002] ; National Natural Science Foundation of China[61871270] ; Shenzhen Science and Technology Program[JCYJ20220530140816037] ; Shenzhen Natural Science Foundation[JCYJ20200109110410133] ; Hong Kong Innovation and Technology Commission (InnoHK) ; Hong Kong General Research Fund-Research Grants Council (GRF-RGC)[11209819] ; Hong Kong General Research Fund-Research Grants Council (GRF-RGC)[9042816] ; Hong Kong General Research Fund-Research Grants Council (GRF-RGC)[11203820] ; Hong Kong General Research Fund-Research Grants Council (GRF-RGC)[9042598]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001045167400070
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[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/2XEOYT63/21372
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Shiqi
作者单位	1.City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China 2.City Univ Hong Kong, Shenzhen Res Inst, Shenzhen 518057, Peoples R China 3.Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China 4.Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China 5.Shenzhen Univ, Guangdong Lab Artificial Intelligence & Digital Ec, Shenzhen 518060, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Pingping,Wang, Shiqi,Wang, Meng,et al. Rethinking Semantic Image Compression: Scalable Representation With Cross-Modality Transfer[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2023,33(8):4441-4445.
APA	Zhang, Pingping,Wang, Shiqi,Wang, Meng,Li, Jiguo,Wang, Xu,&Kwong, Sam.(2023).Rethinking Semantic Image Compression: Scalable Representation With Cross-Modality Transfer.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,33(8),4441-4445.
MLA	Zhang, Pingping,et al."Rethinking Semantic Image Compression: Scalable Representation With Cross-Modality Transfer".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33.8(2023):4441-4445.