Visual Semantic Reasoning for Image-Text Matching

ICCV 2019  ·  Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu ·

Image-text matching has been a hot research topic bridging the vision and language areas. It remains challenging because the current representation of image usually lacks global semantic concepts as in its corresponding text caption. To address this issue, we propose a simple and interpretable reasoning model to generate visual representation that captures key objects and semantic concepts of a scene. Specifically, we first build up connections between image regions and perform reasoning with Graph Convolutional Networks to generate features with semantic relationships. Then, we propose to use the gate and memory mechanism to perform global semantic reasoning on these relationship-enhanced features, select the discriminative information and gradually generate the representation for the whole scene. Experiments validate that our method achieves a new state-of-the-art for the image-text matching on MS-COCO and Flickr30K datasets. It outperforms the current best method by 6.8% relatively for image retrieval and 4.8% relatively for caption retrieval on MS-COCO (Recall@1 using 1K test set). On Flickr30K, our model improves image retrieval by 12.6% relatively and caption retrieval by 5.8% relatively (Recall@1). Our code is available at

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Cross-Modal Retrieval COCO 2014 VSRN Image-to-text R@1 53.0 # 12
Image-to-text R@10 89.4 # 12
Image-to-text R@5 81.1 # 13
Text-to-image R@1 40.5 # 12
Text-to-image R@10 81.1 # 11
Text-to-image R@5 70.6 # 12
Image Retrieval Flickr30K 1K test VSRN R@1 54.7 # 7
R@10 88.2 # 5
R@5 81.8 # 6