Papers › MANGO: A Mask Attention Guided One-Stage Scene Text Spotter

MANGO: A Mask Attention Guided One-Stage Scene Text Spotter

8 Dec 2020arXiv:2012.04350archive 2025-07-28

Liang Qiao, Ying Chen, Zhanzhan Cheng, Yunlu Xu, Yi Niu, ShiLiang Pu, Fei Wu

Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications. Most methods attempt to develop various region of interest (RoI) operations to concatenate the detection part and the sequence recognition part into a two-stage text spotting framework. However, in such framework, the recognition part is highly sensitive to the detected results (e.g.), the compactness of text contours). To address this problem, in this paper, we propose a novel Mask AttentioN Guided One-stage text spotting framework named MANGO, in which character sequences can be directly recognized without RoI operation. Concretely, a position-aware mask attention module is developed to generate attention weights on each text instance and its characters. It allows different text instances in an image to be allocated on different feature map channels which are further grouped as a batch of instance features. Finally, a lightweight sequence decoder is applied to generate the character sequences. It is worth noting that MANGO inherently adapts to arbitrary-shaped text spotting and can be trained end-to-end with only coarse position information (e.g.), rectangular bounding box) and text annotations. Experimental results show that the proposed method achieves competitive and even new state-of-the-art performance on both regular and irregular text spotting benchmarks, i.e., ICDAR 2013, ICDAR 2015, Total-Text, and SCUT-CTW1500.

PaperPDFCode

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

Code

hikopensource/davar-lab-ocr officialmentioned in paperpytorchApache-2.0 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

DecoderText Spottingglobal-optimization

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Spotting ICDAR 2015 MANGO F-measure (%) - Generic Lexicon 67.3 #16 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 MANGO F-measure (%) - Strong Lexicon 81.8 #16 of 18 Archive leaderboard report
Text Spotting ICDAR 2015 MANGO F-measure (%) - Weak Lexicon 78.9 #16 of 18 Archive leaderboard report
Text Spotting SCUT-CTW1500 MANGO F-Measure (%) - Full Lexicon 78.7 #6 of 11 Archive leaderboard report
Text Spotting SCUT-CTW1500 MANGO F-measure (%) - No Lexicon 58.9 #6 of 11 Archive leaderboard report
Text Spotting Total-Text MANGO F-measure (%) - Full Lexicon 83.6 #10 of 12 Archive leaderboard report
Text Spotting Total-Text MANGO F-measure (%) - No Lexicon 72.9 #10 of 12 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