CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 先进机器人
Cross-Modality Synergy Network for Referring Expression Comprehension and Segmentation
Li, Qianzhong1,2; Zhang, Yujia1; Sun, Shiying1; Wu, Jinting1,2; Zhao, Xiaoguang1; Tan, Min1
Source PublicationNeurocomputing
ISSN0925-2312
2022-01-07
Volume467Issue:/Pages:99-114
Abstract

Referring expression comprehension and segmentation aim to locate and segment a referred instance in an image according to a natural language expression. However, existing methods tend to ignore the interaction between visual and language modalities for visual feature learning, and establishing a synergy between the visual and language modalities remains a considerable challenge. To tackle the above problems, we propose a novel end-to-end framework, Cross-Modality Synergy Network (CMS-Net), to address the two tasks jointly. In this work, we propose an attention-aware representation learning module to learn modal representations for both images and expressions. A language self-attention submodule is proposed in this module to learn expression representations by leveraging the intra-modality relations, and a language-guided channel-spatial attention submodule is introduced to obtain the language aware visual representations under language guidance, which helps the model pay more attention to the referent-relevant regions in the images and relieve background interference. Then, we design a cross-modality synergy module to establish the inter-modality relations for modality fusion. Specifically, a language-visual similarity is obtained at each position of the visual feature map, and the synergy is achieved between the two modalities in both semantic and spatial dimensions. Furthermore, we propose a multi-scale feature fusion module with a selective strategy to aggregate the important information from multi-scale features, yielding target results. We conduct extensive experiments on four challenging benchmarks, and our framework achieves significant performance gains over state-of-the-art methods.

KeywordReferring expression comprehension Referring expression segmentation Cross-modality synergy Attention mechanism
DOI10.1016/j.neucom.2021.09.066
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Project of China[2019YFB1310601] ; National Key R&D Program of China[2017YFC0820203-03] ; National Natural Science Foundation of China[62103410]
Funding OrganizationNational Key Research and Development Project of China ; National Key R&D Program of China ; National Natural Science Foundation of China
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000710121100009
PublisherELSEVIER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/46310
Collection复杂系统管理与控制国家重点实验室_先进机器人
Corresponding AuthorZhang, Yujia
Affiliation1.The State Key Laboratory of Management and Control for Complex System, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.chool of Artificial Intelligences, University of Chinese Academy of Sciences, Beijing, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li, Qianzhong,Zhang, Yujia,Sun, Shiying,et al. Cross-Modality Synergy Network for Referring Expression Comprehension and Segmentation[J]. Neurocomputing,2022,467(/):99-114.
APA Li, Qianzhong,Zhang, Yujia,Sun, Shiying,Wu, Jinting,Zhao, Xiaoguang,&Tan, Min.(2022).Cross-Modality Synergy Network for Referring Expression Comprehension and Segmentation.Neurocomputing,467(/),99-114.
MLA Li, Qianzhong,et al."Cross-Modality Synergy Network for Referring Expression Comprehension and Segmentation".Neurocomputing 467./(2022):99-114.
Files in This Item: Download All
File Name/Size DocType Version Access License
Cross-modality syner(4555KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Qianzhong]'s Articles
[Zhang, Yujia]'s Articles
[Sun, Shiying]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Qianzhong]'s Articles
[Zhang, Yujia]'s Articles
[Sun, Shiying]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Qianzhong]'s Articles
[Zhang, Yujia]'s Articles
[Sun, Shiying]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Cross-modality synergy network for referring expression comprehension and segmentation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.