Papers › Graph Structured Network for Image-Text Matching
Graph Structured Network for Image-Text Matching
Chunxiao Liu, Zhendong Mao, Tianzhu Zhang, Hongtao Xie, Bin Wang, Yongdong Zhang
Image-text matching has received growing interest since it bridges vision and language. The key challenge lies in how to learn correspondence between image and text. Existing works learn coarse correspondence based on object co-occurrence statistics, while failing to learn fine-grained phrase correspondence. In this paper, we present a novel Graph Structured Matching Network (GSMN) to learn fine-grained correspondence. The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase. This is achieved by node-level matching and structure-level matching. The node-level matching associates each node with its relevant nodes from another modality, where the node can be object, relation or attribute. The associated nodes then jointly infer fine-grained correspondence by fusing neighborhood associations at structure-level matching. Comprehensive experiments show that GSMN outperforms state-of-the-art methods on benchmarks, with relative Recall@1 improvements of nearly 7% and 2% on Flickr30K and MSCOCO, respectively. Code will be released at: https://github.com/CrossmodalGroup/GSMN.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Cross-Modal Retrieval | Flickr30k | GSMN | Image-to-text R@1 | 76.4 | #18 of 27 | Archive leaderboard | report |
| Cross-Modal Retrieval | Flickr30k | GSMN | Image-to-text R@10 | 97.3 | #18 of 27 | Archive leaderboard | report |
| Cross-Modal Retrieval | Flickr30k | GSMN | Image-to-text R@5 | 94.3 | #18 of 27 | Archive leaderboard | report |
| Cross-Modal Retrieval | Flickr30k | GSMN | Text-to-image R@1 | 57.4 | #18 of 27 | Archive leaderboard | report |
| Cross-Modal Retrieval | Flickr30k | GSMN | Text-to-image R@10 | 89.0 | #18 of 27 | Archive leaderboard | report |
| Cross-Modal Retrieval | Flickr30k | GSMN | Text-to-image R@5 | 82.3 | #18 of 27 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections