SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.06495 · CVPR · 2021

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

Yuxin Wang, Zhendong Mao, Yongdong Zhang, Hongtao Xie, Shancheng Fang

arXiv · PDF · Open in the Atlas

Code that ran

18 of 28 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (11 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 12 have no contract verdict; 5 failures of our instrument; 10 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/2103.06495.json · badge: /api/ran/2103.06495.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
FangShancheng/ABINet marked official in Papers with Code
Papers with Code archive
9 ran · 8 no recorded run
topdu/openocr community
Papers with Code archive
8 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("8b2d895aef15d9be")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

CharsetMapper Ran
ran on a synthesized input · constructed an object; no result was computed
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("94a652daa576d606")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

DecoderUpsample Ran
ran on a synthesized input · constructed an object; no result was computed
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("b0e736ef9fcfc26b")
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 an instance of its own class, DecoderUpsample: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

# DecoderUpsample takes:
# - in_c: int (input channels)
# - out_c: int (output channels)
# - k: int (kernel size, default 3)
# - s: int (stride, default 1)
# - p: int (padding, default 1)
# - mode: str (interpolation mode, default 'nearest')

# For forward(), it expects:
# - x: tensor with shape (batch, in_c, height, width)
# - size: tuple of (height, width) for interpolation target

ARGS = {
    'in_c': 4,
    'out_c': 8,
    'k': 3,
    's': 1,
    'p': 1,
    'mode': 'nearest'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DecoderUpsample — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DecoderUpsample 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
Model Ran
ran on a synthesized input · constructed an object; no result was computed
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("5ff3373e28aae885")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

MultiheadAttention Ran
ran on a synthesized input · constructed an object; no result was computed
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("5dd87791ac034fb5")
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 an instance of its own class, MultiheadAttention: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

class MultiheadAttention(nn.Module):

    def __init__(self, embed_dim, num_heads, dropout=0.0, self_attn=False):
        super(MultiheadAttention, self).__init__()
        self.embed_dim = embed_dim
        self.num_heads = num_heads
        self.head_dim = embed_dim // num_heads
        assert self.head_dim * num_heads == self.embed_dim, 'embed_dim must be divisible by num_heads'
        self.scale = self.head_dim ** (-0.5)
        self.self_attn = self_attn
        if self_attn:
            self.qkv = nn.Linear(embed_dim, embed_dim * 3)
        else:
            self.q = nn.Linear(embed_dim, embed_dim)
            self.kv = nn.Linear(embed_dim, embed_dim * 2)
        self.attn_drop = nn.Dropout(dropout)
        self.out_proj = nn.Linear(embed_dim, embed_dim)

    def forward(self, query, key=None, attn_mask=None):
        B, qN = query.shape[:2]
        if self.self_attn:
            qkv = self.qkv(query)
            qkv = qkv.reshape(B, qN, 3, self.num_heads, self.head_dim).permute(2, 0, 3, 1, 4)
            q, k, v = qkv.unbind(0)
        else:
            kN = key.shape[1]
            q = self.q(query)
            q = q.reshape(B, qN, self.num_heads, self.head_dim).transpose(1, 2)
            kv = self.kv(key)
            kv = kv.reshape(B, kN, 2, self.num_heads, self.head_dim).permute(2, 0, 3, 1, 4)
            k, v = kv.unbind(0)
        attn = q.matmul(k.transpose(2, 3)) * self.scale
        if attn_mask is not None:
            attn += attn_mask
        attn = torch.nn.functional.softmax(attn, dim=-1)
        if not self.training:
            self.attn_map = attn
        attn = self.attn_drop(attn)
        x = attn.matmul(v).transpose(1, 2)
        x = x.reshape(B, qN, self.embed_dim)
        x = self.out_proj(x)
        return x


embed_dim = 4
num_heads = 2
dropout = 0.1
self_attn = True

model = MultiheadAttention(embed_dim=embed_dim, num_heads=num_heads, dropout=dropout, self_attn=self_attn)
model.eval()

batch_size = 2
seq_len_query = 3
query = torch.randn(batch_size, seq_len_query, embed_dim)

ARGS = {
    'embed_dim': embed_dim,
    'num_heads': num_heads,
    'dropout': dropout,
    'self_attn': self_attn,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MultiheadAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MultiheadAttention 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
PositionAttention Ran
ran on a synthesized input · constructed an object; no result was computed
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("a03b5b158fee7dbe")
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 an instance of its own class, PositionAttention: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    'max_length': 10,
    'in_channels': 4,
    'num_channels': 8,
    'mode': 'nearest',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PositionAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PositionAttention 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
PositionalEncoding Ran
ran on a synthesized input · constructed an object; no result was computed
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("c02c1d1f291e2f20")
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 an instance of its own class, PositionalEncoding: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    "dropout": 0.1,
    "dim": 4,
    "max_len": 5000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PositionalEncoding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PositionalEncoding 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
ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("6233cc4fd41851f9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

TransformerBlock Ran
ran on a synthesized input · constructed an object; no result was computed
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("27366919489ba9ab")
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 an instance of its own class, TransformerBlock: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

# Define arguments for TransformerBlock
ARGS = {
    "d_model": 8,
    "nhead": 2,
    "dim_feedforward": 16,
    "attention_dropout_rate": 0.1,
    "residual_dropout_rate": 0.1,
    "with_self_attn": True,
    "with_cross_attn": True,
    "epsilon": 1e-05,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TransformerBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerBlock 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
TransformerDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("226445be82e50d4d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

TransformerEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("1b76a464f3c830a7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

_get_clones Ran
ran; our contract draft was wrong, not the code
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("dcc52ab8e3f774c1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

_get_length Ran
ran, violated the contract we drafted
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("b45dc0a4d0dae7c6")
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 Tensor, ndim 1, dtype family int, shape (2,) 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

torch.manual_seed(0)

# Create a small logit tensor
# Shape: (batch_size=2, sequence_length=4, vocab_size=3)
# The function does argmax on dim=-1, so we need vocab dimension
logit = torch.randn(2, 4, 3)

ARGS = {
    "logit": logit
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, shape (2,) — shape (2,) 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
_get_mask Ran
ran; our contract draft was wrong, not the code
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("edacec1f0c46d5f6")
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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 4) 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

torch.manual_seed(0)

# length: a tensor of sequence lengths with shape [N]
# max_length: an integer representing the maximum sequence length
length = torch.tensor([2, 3])  # batch size 2, with different lengths
max_length = 4

ARGS = {
    "length": length,
    "max_length": max_length,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 4, 4) — shape (2, 1, 4, 4) 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from guanyuezhen/ufcd
pointer only; the stored copy get_code serves, from guanyuezhen/ufcd, is pointer only (licence: NONE) · get_code("6ef392f365cc5703")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. A run is recorded.

encoder_layer Ran
ran; our contract draft was wrong, not the code
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("6d0a2c5e1e8c4121")
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 Sequential. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_c": 3,
    "out_c": 64,
    "k": 3,
    "s": 2,
    "p": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
multi_head_attention_forward Ran
ran; our contract draft was wrong, not the code
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("62abaf6e5036ae75")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

resnet45 Ran
ran on a synthesized input
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("79aaa168270e1981")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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. A run is recorded.

ABINetDecoder Not yet run
unverified (harvested, no recorded run)
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("4fa84ab0bb6d25a1")
How it ran

no invocation recorded.

ABINetModel Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("56724c2edf353bc4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

BCNLanguage Not yet run
unverified (harvested, no recorded run)
topdu/openocr/openrec/modeling/decoders/abinet_decoder.py
code served (permissive licence) · get_code("1e58672f91519c02")
How it ran

no invocation recorded.

BCNLanguage Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("53798f23eb8bbe97")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

BaseAlignment Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("40352875c67d1c69")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

BaseVision Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("b60518783b10d9a4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

MultiheadAttention Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("7c0b340a62978887")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

ResTranformer Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("afb414da038f350c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

TransformerDecoderLayer Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("cf1325762bea9012")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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.

TransformerEncoderLayer Not yet run
unverified (harvested, no recorded run)
FangShancheng/ABINet/modules/model_abinet.py
pointer only (licence: NOASSERTION) · get_code("152fce378f96441c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, FangShancheng/ABINet (NOASSERTION). 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 28 samples lifted from this paper's linked repositories, 28 carry a function identity and 0 do not. Of the 28 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 4 later) and 24 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
conv1x1
brick of this paper's assembly: helper
431 other papers
108 dated earlier, 5 the same month, 312 later, 5 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
_get_clones
brick of this paper's assembly: helper
6 other papers
1 the same month, 5 later · 2 only as an assembly brick
2103.14146 (2021-03)
Describing and Localizing Multiple Changes with Transformers
2108.00202 (2021-08)
HiFT: Hierarchical Feature Transformer for Aerial Tracking
2203.08459 (2022-03)
KinyaBERT: a Morphology-aware Kinyarwanda Language Model
and 3 more not named here
encoder_layer
brick of this paper's assembly: helper
5 other papers
5 later
136880442 (2022 (year only))
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
aaai_19971 (2022 (year only))
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
2305.05140 (2023-05)
Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
and 2 more not named here
multi_head_attention_forward
brick of this paper's assembly: helper
2 other papers
2 later
2305.05140 (2023-05)
Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition
2307.09749 (2023-07)
Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement

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

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from: 1) implicitly language modeling; 2) unidirectional feature representation; and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet for scene text recognition. Firstly, the autonomous suggests to block gradient flow between vision and language models to enforce explicitly language modeling. Secondly, a novel bidirectional cloze network (BCN) as the language model is proposed based on bidirectional feature representation. Thirdly, we propose an execution manner of iterative correction for language model which can effectively alleviate the impact of noise input. Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively. Extensive experiments indicate that ABINet has superiority on lowquality images and achieves state-of-the-art results on several mainstream benchmarks. Besides, the ABINet trained with ensemble self-training shows promising improvement in realizing human-level recognition. Code is available at https://github.com/FangShancheng/ABINet.

For agents

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

get_harvested_code_for_paper("2103.06495")
get_code_for_paper("2103.06495")
have("2103.06495")

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

curl https://syntology.ai/api/ran/2103.06495.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.06495.svg)](https://syntology.ai/paper/2103.06495)

Connect an agent — have() is free.