Papers › Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
Qing Ma, Jiancheng Pan, Cong Bai
Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this problem, we propose a novel Direction-Oriented Visual-semantic Embedding Model (DOVE) to mine the relationship between vision and language. Our highlight is to conduct visual and textual representations in latent space, directing them as close as possible to a redundancy-free regional visual representation. Concretely, a Regional-Oriented Attention Module (ROAM) adaptively adjusts the distance between the final visual and textual embeddings in the latent semantic space, oriented by regional visual features. Meanwhile, a lightweight Digging Text Genome Assistant (DTGA) is designed to expand the range of tractable textual representation and enhance global word-level semantic connections using less attention operations. Ultimately, we exploit a global visual-semantic constraint to reduce single visual dependency and serve as an external constraint for the final visual and textual representations. The effectiveness and superiority of our method are verified by extensive experiments including parameter evaluation, quantitative comparison, ablation studies and visual analysis, on two benchmark datasets, RSICD and RSITMD.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Cross-Modal Retrieval | RSICD | DOVE | Image-to-text R@1 | 8.66% | #7 of 10 | Archive leaderboard | report |
| Cross-Modal Retrieval | RSICD | DOVE | Mean Recall | 22.72% | #7 of 10 | Archive leaderboard | report |
| Cross-Modal Retrieval | RSICD | DOVE | text-to-image R@1 | 6.04% | #7 of 10 | Archive leaderboard | report |
| Cross-Modal Retrieval | RSITMD | DOVE | Image-to-text R@1 | 16.81% | #7 of 10 | Archive leaderboard | report |
| Cross-Modal Retrieval | RSITMD | DOVE | Mean Recall | 37.73% | #7 of 10 | Archive leaderboard | report |
| Cross-Modal Retrieval | RSITMD | DOVE | text-to-imageR@1 | 12.20% | #7 of 10 | 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