Visual Semantic Reasoning for Image-Text Matching
This work addresses the problem of bridging vision and language for researchers and practitioners in AI, though it appears incremental as it builds on existing methods like Graph Convolutional Networks.
The paper tackled the challenge of image-text matching by addressing the lack of global semantic concepts in image representations, proposing a visual semantic reasoning model that achieved new state-of-the-art results, with relative improvements of 6.8% for image retrieval and 4.8% for caption retrieval on MS-COCO, and 12.6% and 5.8% on Flickr30K.
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 https://github.com/KunpengLi1994/VSRN.