Papers › Single Shot Text Detector with Regional Attention
Single Shot Text Detector with Regional Attention
Pan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, Xiaolin Li
We present a novel single-shot text detector that directly outputs word-level bounding boxes in a natural image. We propose an attention mechanism which roughly identifies text regions via an automatically learned attentional map. This substantially suppresses background interference in the convolutional features, which is the key to producing accurate inference of words, particularly at extremely small sizes. This results in a single model that essentially works in a coarse-to-fine manner. It departs from recent FCN- based text detectors which cascade multiple FCN models to achieve an accurate prediction. Furthermore, we develop a hierarchical inception module which efficiently aggregates multi-scale inception features. This enhances local details, and also encodes strong context information, allow- ing the detector to work reliably on multi-scale and multi- orientation text with single-scale images. Our text detector achieves an F-measure of 77% on the ICDAR 2015 bench- mark, advancing the state-of-the-art results in [18, 28]. Demo is available at: http://sstd.whuang.org/.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Scene Text Detection | COCO-Text | SSTD | F-Measure | 37 | #4 of 6 | Archive leaderboard | report |
| Scene Text Detection | COCO-Text | SSTD | Precision | 46 | #4 of 6 | Archive leaderboard | report |
| Scene Text Detection | COCO-Text | SSTD | Recall | 31 | #4 of 6 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | SSTD | F-Measure | 87% | #10 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | SSTD | Precision | 88 | #10 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2013 | SSTD | Recall | 86 | #10 of 16 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | EAST + PVANET2x RBOX (multi-scale) | F-Measure | 80.7 | #36 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | EAST + PVANET2x RBOX (multi-scale) | Precision | 83.3 | #36 of 43 | Archive leaderboard | report |
| Scene Text Detection | ICDAR 2015 | EAST + PVANET2x RBOX (multi-scale) | Recall | 78.3 | #36 of 43 | 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.
Methods
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