SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1704.03155 · 2017

EAST: An Efficient and Accurate Scene Text Detector

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1704.03155.json · badge: /api/ran/1704.03155.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yakhyo/east-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
SakuraRiven/EAST reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
Chris10M/RFB-Text-Detection extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
argman/EAST reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_path_list Ran
ran; our contract draft was wrong, not the code
Chris10M/RFB-Text-Detection/run_demo.py
code served (permissive licence) · get_code("2810b57a93d7c863")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import shutil

# Create a temporary directory structure with some image files
temp_dir = tempfile.mkdtemp()

# Create subdirectories
subdir1 = os.path.join(temp_dir, "subdir1")
subdir2 = os.path.join(temp_dir, "subdir2")
os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)

# Create some dummy image files (empty files with image extensions)
image_files = [
    os.path.join(temp_dir, "image1.jpg"),
    os.path.join(temp_dir, "image2.PNG"),
    os.path.join(subdir1, "photo.jpeg"),
    os.path.join(subdir1, "picture.bmp"),
    os.path.join(subdir2, "test.jpg"),
]

# Create the files
for filepath in image_files:
    with open(filepath, 'w') as f:
        f.write("")

# Also create a non-image file that should be ignored
with open(os.path.join(temp_dir, "readme.txt"), 'w') as f:
    f.write("")

ARGS = {
    "root_path": temp_dir
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_valid_poly Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yakhyo/east-pytorch/detect.py
code served (permissive licence) · get_code("d683e0b7226e6e35")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# The function checks if a polygon (res) is within bounds defined by score_shape and scale
# res is expected to be a 2D array/tensor with shape (2, num_points) where:
#   - res[0, :] are x-coordinates
#   - res[1, :] are y-coordinates
# score_shape is a tuple/list with (height, width)
# scale is a scalar that multiplies score_shape to get image dimensions

# Create a valid polygon with 4 points
# Let's make it within bounds: score_shape = (10, 12), scale = 2
# So valid x range is [0, 12*2) = [0, 24)
# Valid y range is [0, 10*2) = [0, 20)

res = np.array([
    [5.0, 10.0, 15.0, 8.0],   # x-coordinates
    [3.0, 7.0, 12.0, 5.0]     # y-coordinates
])

score_shape = (10, 12)  # (height, width)
scale = 2

ARGS = {
    'res': res,
    'score_shape': score_shape,
    'scale': scale
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_valid_poly Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SakuraRiven/EAST/detect.py
code served (permissive licence) · get_code("66e30af743cc4a1a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# The function checks if a polygon (res) is within bounds defined by score_shape and scale
# res has shape (2, n) where res[0, :] are x-coordinates and res[1, :] are y-coordinates
# score_shape is a tuple/list with (height, width)
# scale is a scalar that multiplies score_shape to get image dimensions

# Create a valid polygon with 4 points (2D coordinates)
res = np.array([
    [10.0, 20.0, 30.0, 25.0],  # x-coordinates
    [15.0, 25.0, 35.0, 20.0]   # y-coordinates
])

# score_shape as (height, width)
score_shape = (50, 60)

# scale factor
scale = 2

ARGS = {
    'res': res,
    'score_shape': score_shape,
    'scale': scale
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
resize Ran
ran; our contract draft was wrong, not the code
yakhyo/east-pytorch/detect.py
code served (permissive licence) · get_code("e55b33eadf6b16e5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from PIL import Image, ImageDraw

# Create a small test image with dimensions not divisible by 32
# Using 100x75 so we can test the resize logic
width = 100
height = 75
image = Image.new('RGB', (width, height), color='red')

ARGS = {
    'image': image
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
resize_img Ran
ran; our contract draft was wrong, not the code
SakuraRiven/EAST/detect.py
code served (permissive licence) · get_code("31e0255b8c515ebb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from PIL import Image

# Create a small test image with dimensions not divisible by 32
# Using 100x75 so that resizing will actually change dimensions
img = Image.new('RGB', (100, 75), color='red')

ARGS = {
    'img': img
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_predictor Not yet run
unverified (harvested, no recorded run)
argman/EAST/run_demo_server.py
pointer only (licence: GPL-3.0) · get_code("85d1fadaaf9cb100")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, argman/EAST, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
resize_img 1 other paper
1 dated earlier
1512.02595 (2015-12)
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1704.03155")
get_code_for_paper("1704.03155")
have("1704.03155")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1704.03155.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1704.03155.svg)](https://syntology.ai/paper/1704.03155)

Connect an agent — have() is free.