3SHNet: Boosting image-sentence retrieval via visual semantic-spatial self-highlighting

Ge, X. , Xu, S., Chen, F., Wang, J., Wang, G., An, S. and Jose, J. M. (2024) 3SHNet: Boosting image-sentence retrieval via visual semantic-spatial self-highlighting. Information Processing and Management, 61(4), 103716. (doi: 10.1016/j.ipm.2024.103716)

Abstract

In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image–sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics–spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%.

• Item Type: Articles
• Additional Information: Fuhai Chen’s research was supported in part by the Fujian Provincial Department of Education Youth Project (grant JZ230006) and the Engineering Research Center of Big Data Intelligence, Ministry of Education, and Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University); Xuri Ge’s research was supported in part by China Scholarship Council (CSC) from the Ministry of Education of China (No. 202006310028).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Jose, Professor Joemon and Wang, Miss Jie and Ge, Xuri and Xu, Ms Songpei

Creator Roles

Ge, X.: Writing – review and editing, Writing – original draft, Visualization, Validation, Supervision, Resources, Project administration, Methodology, Data curation
Xu, S.: Writing – original draft, Visualization, Resources, Methodology
Wang, J.: Writing – review and editing, Data curation
Jose, J.: Writing – review and editing, Resources, Methodology, Conceptualization

• Authors: Ge, X., Xu, S., Chen, F., Wang, J., Wang, G., An, S., and Jose, J. M.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Information Processing and Management
• Publisher: Elsevier
• ISSN: 0306-4573
• ISSN (Online): 1873-5371
• Published Online: 20 March 2024