Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval

Sijin Wang, Ruiping Wang, Ziwei Yao, Shiguang Shan, Xilin Chen; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1508-1517

Abstract


Image-text retrieval of natural scenes has been a popular research topic. Since image and text are heterogeneous cross-modal data, one of the key challenges is how to learn comprehensive yet unified representations to express the multi-modal data. A natural scene image mainly involves two kinds of visual concepts, objects and their relationships, which are equally essential to image-text retrieval. Therefore, a good representation should account for both of them. In the light of recent success of scene graph in many CV and NLP tasks for describing complex natural scenes, we propose to represent image and text with two kinds of scene graphs: visual scene graph (VSG) and textual scene graph (TSG), each of which is exploited to jointly characterize objects and relationships in the corresponding modality. The image-text retrieval task is then naturally formulated as cross-modal scene graph matching. Specifically, we design two particular scene graph encoders in our model for VSG and TSG, which can refine the representation of each node on the graph by aggregating neighborhood information. As a result, both object-level and relationship-level cross-modal features can be obtained, which favorably enables us to evaluate the similarity of image and text in the two levels in a more plausible way. We achieve state-of-the-art results on Flickr30k and MS COCO, which verifies the advantages of our graph matching based approach for image-text retrieval.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2020_WACV,
author = {Wang, Sijin and Wang, Ruiping and Yao, Ziwei and Shan, Shiguang and Chen, Xilin},
title = {Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}