Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval

Ge, X., Chen, F., Xu, S., Tao, F. and Jose, J. M. (2023) Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), Waikoloa, Hawaii, 3-7 Jan 2023, pp. 1022-1031. ISBN 9781665493468 (doi: 10.1109/WACV56688.2023.00108)

[img] Text
282102.pdf - Accepted Version



Image-sentence retrieval has attracted extensive research attention in multimedia and computer vision due to its promising application. The key issue lies in jointly learning the visual and textual representation to accurately estimate their similarity. To this end, the mainstream schema adopts an object-word based attention to calculate their relevance scores and refine their interactive representations with the attention features, which, however, neglects the context of the object representation on the inter-object relationship that matches the predicates in sentences. In this paper, we propose a Cross-modal Semantic Enhanced Interaction method, termed CMSEI for image-sentence retrieval, which correlates the intra- and inter-modal semantics be-tween objects and words. In particular, we first design the intra-modal spatial and semantic graphs based reasoning to enhance the semantic representations of objects guided by the explicit relationships of the objects’ spatial positions and their scene graph. Then the visual and textual semantic representations are refined jointly via the inter-modal interactive attention and the cross-modal alignment. To correlate the context of objects with the textual context, we further refine the visual semantic representation via the cross-level object-sentence and word-image based interactive attention. Experimental results on seven standard evaluation metrics show that the proposed CMSEI outperforms the state-of-the-art and the alternative approaches on MS-COCO and Flickr30K benchmarks.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Jose, Professor Joemon and Tao, Mr Fuxiang and Ge, Ms Xuri and Xu, Ms Songpei
Authors: Ge, X., Chen, F., Xu, S., Tao, F., and Jose, J. M.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2023 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record