Papers › FOTS: Fast Oriented Text Spotting with a Unified Network

FOTS: Fast Oriented Text Spotting with a Unified Network

5 Jan 2018CVPR 2018 6arXiv:1801.01671archive 2025-07-28

Xuebo Liu, Ding Liang, Shi Yan, Dagui Chen, Yu Qiao, Junjie Yan

Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and recognition as separate tasks. In this work, we propose a unified end-to-end trainable Fast Oriented Text Spotting (FOTS) network for simultaneous detection and recognition, sharing computation and visual information among the two complementary tasks. Specially, RoIRotate is introduced to share convolutional features between detection and recognition. Benefiting from convolution sharing strategy, our FOTS has little computation overhead compared to baseline text detection network, and the joint training method learns more generic features to make our method perform better than these two-stage methods. Experiments on ICDAR 2015, ICDAR 2017 MLT, and ICDAR 2013 datasets demonstrate that the proposed method outperforms state-of-the-art methods significantly, which further allows us to develop the first real-time oriented text spotting system which surpasses all previous state-of-the-art results by more than 5% on ICDAR 2015 text spotting task while keeping 22.6 fps.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ArashJavan/FOTS mentioned on GitHubtf report
Kaushal28/FOTS-PyTorch mentioned on GitHubpytorch report
Masao-Taketani/FOTS_OCR mentioned on GitHubtf report
Pay20Y/FOTS_TF mentioned on GitHubtf report
jiangxiluning/FOTS.PyTorch mentioned on GitHubpytorch report

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

Scene Text DetectionScene Text RecognitionText DetectionText Spotting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2015 FOTS MS F-Measure 89.84 #7 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 FOTS MS Precision 91.85 #7 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 FOTS MS Recall 87.92 #7 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 FOTS F-Measure 87.99 #12 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 FOTS Precision 91 #12 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 FOTS Recall 85.17 #12 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT FOTS MS F-Measure 70.75% #4 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT FOTS MS Precision 81.86 #4 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT FOTS MS Recall 62.3 #4 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT FOTS F-Measure 67.25% #6 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT FOTS Precision 80.95 #6 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT FOTS Recall 57.51 #6 of 14 Archive leaderboard report
Text Spotting ICDAR 2015 FOTS F-measure (%) - Generic Lexicon 62.2 #10 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 FOTS F-measure (%) - Strong Lexicon 83.6 #10 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 FOTS F-measure (%) - Weak Lexicon 74.5 #10 of 18 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

Convolution

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