Papers › TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

4 Jul 2018ECCV 2018 9arXiv:1807.01544archive 2025-07-28

Shangbang Long, Jiaqiang Ruan, Wenjie Zhang, Xin He, Wenhao Wu, Cong Yao

Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the representations (axis-aligned rectangles, rotated rectangles or quadrangles) adopted to describe text, existing methods may fall short when dealing with much more free-form text instances, such as curved text, which are actually very common in real-world scenarios. To tackle this problem, we propose a more flexible representation for scene text, termed as TextSnake, which is able to effectively represent text instances in horizontal, oriented and curved forms. In TextSnake, a text instance is described as a sequence of ordered, overlapping disks centered at symmetric axes, each of which is associated with potentially variable radius and orientation. Such geometry attributes are estimated via a Fully Convolutional Network (FCN) model. In experiments, the text detector based on TextSnake achieves state-of-the-art or comparable performance on Total-Text and SCUT-CTW1500, the two newly published benchmarks with special emphasis on curved text in natural images, as well as the widely-used datasets ICDAR 2015 and MSRA-TD500. Specifically, TextSnake outperforms the baseline on Total-Text by more than 40% in F-measure.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 2 repositories, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

princewang1994/TextSnake.pytorch mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
speakstone/TextSnake mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
open-mmlab/mmocr pytorchApache-2.0Syntology: not harvested 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
5ran

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

princewang1994/TextSnake.pytorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
make_layers in 155 papers network/vgg.py ran · our draft was wrong MIT (permissive) · ac62432dc5134b0d · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
pil_load_img dataset/dataload.py ran MIT (permissive) · 82860b18e1fc22c2 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-26
speakstone/TextSnake community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
get in 42 papers dataset/data_coco.py ran MIT (permissive) · d2f61d806e44b0a6 · report fixture: signature root:Element/0/?, name:str/0/str · returned list · level recorded 2026-09-26
get_and_check dataset/data_coco.py ran MIT (permissive) · 9df01a1787744a19 · report fixture: signature root:Element/0/?, name:str/0/str, length:int/0/int · returned list · level recorded 2026-09-26
get_filename_as_int dataset/data_coco.py ran MIT (permissive) · 138a54613786d206 · report fixture: signature filename:str/0/str · returned int · level recorded 2026-09-26
md5sum bai_pachong/Img_Deduplication.py ran MIT (permissive) · 1dcd42e5770df07d · report fixture: signature filename:str/0/str · returned str · level recorded 2026-09-26

Tasks

Curved Text DetectionScene Text DetectionText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Curved Text Detection SCUT-CTW1500 TextSnake [[Long et al.(2018)Long, Ruan, Zhang, He, Wu, and Yao]] F-Measure 75.6% #2 of 5 Archive leaderboard report
Scene Text Detection ICDAR 2015 PixelLink+VGG16 2s F-Measure 83.7 #29 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PixelLink+VGG16 2s Precision 85.5 #29 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PixelLink+VGG16 2s Recall 82 #29 of 43 Archive leaderboard report
Scene Text Detection MSRA-TD500 TextSnake F-Measure 78.3 #15 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 TextSnake Precision 83.2 #15 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 TextSnake Recall 73.9 #15 of 18 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 TextSnake F-Measure 75.6 #16 of 17 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 TextSnake Precision 67.9 #16 of 17 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 TextSnake Recall 85.3 #16 of 17 Archive leaderboard report
Scene Text Detection Total-Text TextSnake F-Measure 78.4% #24 of 27 Archive leaderboard report
Scene Text Detection Total-Text TextSnake Precision 82.7 #24 of 27 Archive leaderboard report
Scene Text Detection Total-Text TextSnake Recall 74.5 #24 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