SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.00751 · 2018

Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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 7 have no contract verdict; 0 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/1811.00751.json · badge: /api/ran/1811.00751.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
liuch37/sar-pytorch community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
phantrdat/cvpr20-scatter-text-recognizer community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
tobiasvanderwerff/MetaHTR community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
attention_map Ran
ran on a synthesized input
liuch37/sar-pytorch/utils/attention_map.py
code served (permissive licence) · get_code("deda6831eb0cc4f0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 5, dtype family int; 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small image tensor [C, H, W] in BGR order, normalized to [-1, 1]
# Using shape [3, 32, 40] for distinct dimensions
image_tensor = torch.randn(3, 32, 40) * 2 - 1  # normalize to approximately [-1, 1]

# Create attention weights tensor [seq_len, 1, feature_H, feature_W] in [0, 1]
# seq_len = 5 (length of predicted word)
# feature dimensions are smaller than image: [1, 8, 10]
attention_weights = torch.rand(5, 1, 8, 10)  # values in [0, 1]

# Predicted word string
predicted_word = "hello"

ARGS = {
    "predict_word": predicted_word,
    "x": image_tensor,
    "attention_weight": attention_weights
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 5, dtype family int — a tuple 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
checkImageIsValid Ran
ran on a synthesized input
phantrdat/cvpr20-scatter-text-recognizer/create_lmdb_dataset.py
code served (permissive licence) · get_code("c7b92e1633b0d2da")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) 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 cv2
import numpy as np

# Create a valid image in binary format
# Create a simple 10x8 grayscale image (10 height, 8 width)
img = np.random.randint(0, 256, size=(10, 8), dtype=np.uint8)
# Encode to PNG format (or any format that cv2.imdecode can read)
success, imageBin = cv2.imencode('.png', img)
imageBin = imageBin.tobytes()

ARGS = {
    "imageBin": imageBin
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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
dictionary_generator Ran
ran on a synthesized input
liuch37/sar-pytorch/dataset/dataset.py
code served (permissive licence) · get_code("d00e42d99ad77876")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) 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.

import string

ARGS = {
    'END': 'END',
    'PADDING': 'PAD',
    'UNKNOWN': 'UNK'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
end_cut Ran
ran on a synthesized input
liuch37/sar-pytorch/dataset/dataset.py
code served (permissive licence) · get_code("432c3464425adb58")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. 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.

import numpy as np

# Create character to id and id to character mappings
char2id = {
    'END': 0,
    'UNK': 1,
    'PAD': 2,
    'a': 3,
    'b': 4,
    'c': 5,
    'd': 6,
}

id2char = {
    0: 'END',
    1: 'UNK',
    2: 'PAD',
    3: 'a',
    4: 'b',
    5: 'c',
    6: 'd',
}

# Create sample indices that include valid characters, UNK, PAD, and END
indices = np.array([3, 4, 5, 1, 2, 6, 0, 3], dtype=np.int32)

ARGS = {
    'indices': indices,
    'char2id': char2id,
    'id2char': id2char,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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_pl_tb_logger Ran
ran on a synthesized input
tobiasvanderwerff/MetaHTR/metahtr/util.py
code served (permissive licence) · get_code("7110cd886f2674e9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned TensorBoardLogger. 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.

import torch
from pathlib import Path
from pytorch_lightning import loggers as pl_loggers
import tempfile

# Create a temporary directory for logging
temp_dir = tempfile.mkdtemp()

ARGS = {
    "log_dir": temp_dir,
    "version": "test_version_0"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pytorch_lightning, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TensorBoardLogger — a TensorBoardLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TensorBoardLogger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
svt_xml_extractor Ran
ran on a synthesized input
liuch37/sar-pytorch/dataset/dataset.py
code served (permissive licence) · get_code("df31f55edb95b761")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. 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.

import xml.etree.ElementTree as ET
import tempfile
import os

# Create a temporary XML file matching SVT dataset format
xml_content = """<?xml version="1.0" encoding="UTF-8"?>
<dataset>
    <image>
        <imageName>path/to/image1.jpg</imageName>
        <lex>hello,world,test</lex>
        <taggedRectangles>
            <taggedRectangle x="10" y="20" width="100" height="50">
                <tag>hello</tag>
            </taggedRectangle>
            <taggedRectangle x="120" y="30" width="80" height="40">
                <tag>world</tag>
            </taggedRectangle>
        </taggedRectangles>
    </image>
    <image>
        <imageName>path/to/image2.jpg</imageName>
        <lex>foo,bar</lex>
        <taggedRectangles>
            <taggedRectangle x="5" y="15" width="60" height="35">
                <tag>foo</tag>
            </taggedRectangle>
        </taggedRectangles>
    </image>
</dataset>
"""

# Write to temporary file
with tempfile.NamedTemporaryFile(mode='w', suffix='.xml', delete=False) as f:
    f.write(xml_content)
    temp_xml_path = f.name

try:
    ARGS = {
        'label_path': temp_xml_path
    }
finally:
    # Note: In actual execution, you'd clean up with os.unlink(temp_xml_path)
    # but keeping file alive for function execution
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 — a list 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
tensor2im Ran
ran on a synthesized input
phantrdat/cvpr20-scatter-text-recognizer/dataset.py
code served (permissive licence) · get_code("b78e81e855133e45")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 3, 3) 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small image tensor with shape (C, H, W)
# Using shape (1, 4, 3) - 1 channel, 4 height, 3 width
# Values in range [-1, 1] as expected by the function
image_tensor = torch.randn(1, 4, 3)

ARGS = {
    "image_tensor": image_tensor,
    "imtype": np.uint8
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) 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
copy_hyperparameters_to_logging_dir Not yet run
unverified (harvested, no recorded run)
tobiasvanderwerff/MetaHTR/metahtr/util.py
code served (permissive licence) · get_code("73cdf16e24a09a8c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 6 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
tensor2im 4 other papers
4 later
1904.01906 (2019-04)
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
1906.01502 (2019-06)
How multilingual is Multilingual BERT?
2207.04675 (2022-07)
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
and 1 more not named here
checkImageIsValid 3 other papers
3 later
1904.01906 (2019-04)
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
2207.04675 (2022-07)
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
2305.05140 (2023-05)
Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition

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

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

Abstract

Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion. Most existing approaches rely heavily on sophisticated model designs and/or extra fine-grained annotations, which, to some extent, increase the difficulty in algorithm implementation and data collection. In this work, we propose an easy-to-implement strong baseline for irregular scene text recognition, using off-the-shelf neural network components and only word-level annotations. It is composed of a $31$-layer ResNet, an LSTM-based encoder-decoder framework and a 2-dimensional attention module. Despite its simplicity, the proposed method is robust and achieves state-of-the-art performance on both regular and irregular scene text recognition benchmarks. Code is available at: https://tinyurl.com/ShowAttendRead

For agents

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

get_harvested_code_for_paper("1811.00751")
get_code_for_paper("1811.00751")
have("1811.00751")

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

curl https://syntology.ai/api/ran/1811.00751.json

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

[![Syntology run record](https://syntology.ai/api/ran/1811.00751.svg)](https://syntology.ai/paper/1811.00751)

Connect an agent — have() is free.