SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.04722 · ICCV · 2021

Transformer-based Dual Relation Graph for Multi-label Image Recognition

Jia Li, Jiawei Zhao, Ke Yan, Yifan Zhao, Feiyue Huang, Xiaowei Guo, Tencent Youtu

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 1 failure of our instrument; 3 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/2110.04722.json · badge: /api/ran/2110.04722.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
iCVTEAM/TDRG marked official in Papers with Code
Papers with Code archive
9 ran · 3 no recorded run
FunctionStatusWhere it lives
GraphConvolution Ran
ran on a synthesized input · constructed an object; no result was computed
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("4af7cba6f2b6a00b")
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, GraphConvolution: 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)

# Analyze the forward method:
# - adj: used in torch.matmul(nodes, adj), so needs shape compatible with nodes
# - nodes: input tensor, goes through matmul with adj, then relu, then Conv1d
# 
# Conv1d expects input of shape (batch, in_dim, length) or (batch, in_dim)
# So nodes should have shape (batch, in_dim, seq_len) where seq_len could be 1
# adj should be (seq_len, seq_len) or similar to work with matmul
# 
# Let's use:
# - batch_size = 2
# - in_dim = 4
# - seq_len = 3
# - out_dim = 5

in_dim = 4
out_dim = 5
batch_size = 2
seq_len = 3

# Create adj matrix: (seq_len, seq_len)
adj = torch.randn(seq_len, seq_len)

# Create nodes tensor: (batch, in_dim, seq_len)
nodes = torch.randn(batch_size, in_dim, seq_len)

ARGS = {
    "in_dim": in_dim,
    "out_dim": out_dim,
}
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 GraphConvolution — 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 GraphConvolution 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
PositionEmbeddingLearned Ran
ran on a synthesized input · constructed an object; no result was computed
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("0fdd4b27f23fb10e")
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, PositionEmbeddingLearned: 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 PositionEmbeddingLearned(nn.Module):
    """
    Absolute pos embedding, learned.
    """

    def __init__(self, num_pos_feats=256):
        super(PositionEmbeddingLearned, self).__init__()
        self.row_embed = nn.Embedding(50, num_pos_feats)
        self.col_embed = nn.Embedding(50, num_pos_feats)
        self.reset_parameters()

    def reset_parameters(self):
        nn.init.uniform_(self.row_embed.weight)
        nn.init.uniform_(self.col_embed.weight)

    def forward(self, x):
        h, w = x.shape[-2:]
        i = torch.arange(w, device=x.device)
        j = torch.arange(h, device=x.device)
        x_emb = self.col_embed(i)
        y_emb = self.row_embed(j)
        pos = torch.cat([x_emb.unsqueeze(0).repeat(h, 1, 1), y_emb.unsqueeze(1).repeat(1, w, 1)], dim=-1).permute(2, 0, 1).unsqueeze(0).repeat(x.shape[0], 1, 1, 1)
        return pos

# Create test input tensor: batch_size=2, channels=4, height=3, width=5
test_input = torch.randn(2, 4, 3, 5)

# Test the module instantiation and forward pass
model = PositionEmbeddingLearned(num_pos_feats=256)
output = model(test_input)

ARGS = {
    "num_pos_feats": 256
}
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 PositionEmbeddingLearned — 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 PositionEmbeddingLearned 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
PositionEmbeddingSine Ran
ran on a synthesized input
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("19ad134c39cefe3a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, 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 torch
import torch.nn as nn
import math

class PositionEmbeddingSine(nn.Module):
    """
    This is a more standard version of the position embedding, very similar to the one
    used by the Attention is all you need paper, generalized to work on images.
    """

    def __init__(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None):
        super(PositionEmbeddingSine, self).__init__()
        self.num_pos_feats = num_pos_feats
        self.temperature = temperature
        self.normalize = normalize
        if scale is not None and normalize is False:
            raise ValueError('normalize should be True if scale is passed')
        if scale is None:
            scale = 2 * math.pi
        self.scale = scale

    def forward(self, x, mask):
        assert mask is not None
        not_mask = ~mask
        y_embed = not_mask.cumsum(1, dtype=torch.float32)
        x_embed = not_mask.cumsum(2, dtype=torch.float32)
        if self.normalize:
            eps = 1e-06
            y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
            x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale
        dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
        dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats)
        pos_x = x_embed[:, :, :, None] / dim_t
        pos_y = y_embed[:, :, :, None] / dim_t
        pos_x = torch.stack((pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4).flatten(3)
        pos_y = torch.stack((pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4).flatten(3)
        pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)
        return pos

INIT_ARGS = {
    'num_pos_feats': 32,
    'temperature': 10000,
    'normalize': True,
    'scale': 2 * math.pi
}

batch_size = 2
height = 5
width = 7
channels = 16

x = torch.randn(batch_size, channels, height, width)
mask = torch.zeros(batch_size, height, width, dtype=torch.bool)
mask[0, 2:4, 3:5] = True
mask[1, 0:2, 1:3] = True

ARGS = {
    'x': x,
    'mask': mask
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
TopKMaxPooling Ran
ran on a synthesized input
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("b98e254770325b03")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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 torch
import torch.nn as nn

# INIT_ARGS: parameters for TopKMaxPooling.__init__
INIT_ARGS = {
    'kmax': 0.5  # Take top 50% of spatial locations
}

# ARGS: parameters for TopKMaxPooling.forward
# Input should be a 4D tensor: (batch_size, num_channels, height, width)
ARGS = {
    'input': torch.randn(2, 3, 4, 5)  # batch=2, channels=3, height=4, width=5
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
TransformerDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("e3629529c763edf7")
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, TransformerDecoder: 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 copy

torch.manual_seed(0)

# Build a minimal decoder layer that matches the interface expected
class SimpleDecoderLayer(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.linear = nn.Linear(d_model, d_model)
    
    def forward(self, tgt, memory, tgt_mask=None, memory_mask=None, 
                tgt_key_padding_mask=None, memory_key_padding_mask=None, 
                pos=None, query_pos=None):
        # Simple forward: just process tgt through linear layer
        return self.linear(tgt)

# Build a minimal norm layer
norm_layer = nn.LayerNorm(4)

# Create decoder layer instance
decoder_layer = SimpleDecoderLayer(d_model=4)

# Create number of layers
num_layers = 2

ARGS = {
    "decoder_layer": decoder_layer,
    "num_layers": num_layers,
    "norm": norm_layer,
    "return_intermediate": False
}
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 TransformerDecoder — 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 TransformerDecoder 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
TransformerDecoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("a1044a3d81853ba9")
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, TransformerDecoderLayer: 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for the decoder layer
batch_size = 2
seq_len_tgt = 3
seq_len_memory = 5
d_model = 4
nhead = 2
dim_feedforward = 8

# Target tensor (query)
tgt = torch.randn(seq_len_tgt, batch_size, d_model)

# Memory tensor (key/value from encoder)
memory = torch.randn(seq_len_memory, batch_size, d_model)

# Positional embeddings (optional)
pos = torch.randn(seq_len_memory, batch_size, d_model)
query_pos = torch.randn(seq_len_tgt, batch_size, d_model)

# Attention masks (optional)
tgt_mask = None
memory_mask = None

# Key padding masks (optional)
tgt_key_padding_mask = None
memory_key_padding_mask = None

ARGS = {
    'd_model': d_model,
    'nhead': nhead,
    'dim_feedforward': dim_feedforward,
    'dropout': 0.1,
    'activation': 'relu',
    'normalize_before': False,
}
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 TransformerDecoderLayer — 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 TransformerDecoderLayer 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
TransformerEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("8ee0966a4a5305fa")
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, TransformerEncoder: 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 copy

torch.manual_seed(0)

# Create a minimal encoder layer that matches the expected interface
class MinimalEncoderLayer(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.d_model = d_model
        self.linear = nn.Linear(d_model, d_model)
    
    def forward(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        # The function calls this with src and optional mask/pos arguments
        return self.linear(src)

# Create a minimal norm layer
norm_layer = nn.LayerNorm(4)

# Create encoder layer instance
encoder_layer = MinimalEncoderLayer(d_model=4)

# Number of layers to clone
num_layers = 2

ARGS = {
    'encoder_layer': encoder_layer,
    'num_layers': num_layers,
    'norm': norm_layer
}
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 TransformerEncoder — 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 TransformerEncoder 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
TransformerEncoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("4a32b2ac8f43376e")
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, TransformerEncoderLayer: 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 torch.nn.functional as F

torch.manual_seed(0)

def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == 'relu':
        return F.relu
    if activation == 'gelu':
        return F.gelu
    if activation == 'glu':
        return F.glu
    raise RuntimeError('activation should be relu/gelu, not {activation}.')

class TransformerEncoderLayer(nn.Module):

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation='relu', normalize_before=False):
        super(TransformerEncoderLayer, self).__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)
        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def with_pos_embed(self, tensor, pos=None):
        return tensor if pos is None else tensor + pos

    def without_pos_embed(self, tensor, pos=None):
        return tensor

    def forward_post(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        q = k = self.with_pos_embed(src, pos)
        src2 = self.self_attn(q, k, value=src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src

    def forward_pre(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        src2 = self.norm1(src)
        q = k = self.with_pos_embed(src2, pos)
        src2 = self.self_attn(q, k, value=src2, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src2 = self.norm2(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src2))))
        src = src + self.dropout2(src2)
        return src

    def forward(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        if self.normalize_before:
            return self.forward_pre(src, src_mask, src_key_padding_mask, pos)
        return self.forward_post(src, src_mask, src_key_padding_mask, pos)

# Create tiny tensors for testing
# src shape: (seq_len, batch_size, d_model)
src = torch.randn(3, 2, 4)
pos = torch.randn(3, 2, 4)

ARGS = {
    'd_model': 4,
    'nhead': 2,
    'dim_feedforward': 8,
    'dropout': 0.1,
    'activation': 'relu',
    'normalize_before': False,
}
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 TransformerEncoderLayer — 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 TransformerEncoderLayer 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
build_position_encoding Ran
ran; our contract draft was wrong, not the code
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("626421743e751cfd")
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 PositionEmbeddingSine. 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 = {
    'hidden_dim': 128,
    'mode': 'sine'
}
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 PositionEmbeddingSine — a PositionEmbeddingSine output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PositionEmbeddingSine 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
TDRG Not yet run
unverified (harvested, no recorded run)
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("e32b7a1a6935ef81")
How it ran

no invocation recorded.

Transformer Not yet run
unverified (harvested, no recorded run)
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("a6af96a295df827c")
How it ran

no invocation recorded.

build_transformer Not yet run
unverified (harvested, no recorded run)
iCVTEAM/TDRG/models/TDRG.py
code served (permissive licence) · get_code("2a6ad2bf42c596fb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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.

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

The simultaneous recognition of multiple objects in one image remains a challenging task, spanning multiple events in the recognition field such as various object scales, inconsistent appearances, and confused inter-class relationships. Recent research efforts mainly resort to the statistic label co-occurrences and linguistic word embedding to enhance the unclear semantics. Different from these researches, in this paper, we propose a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i.e., structural relation graph and semantic relation graph. The structural relation graph aims to capture long-range correlations from object context, by developing a cross-scale transformer-based architecture. The semantic graph dynamically models the semantic meanings of image objects with explicit semantic-aware constraints. In addition, we also incorporate the learnt structural relationship into the semantic graph, constructing a joint relation graph for robust representations. With the collaborative learning of these two effective relation graphs, our approach achieves new state-of-the-art on two popular multi-label recognition benchmarks, i.e. MS-COCO and VOC 2007 dataset.

For agents

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

get_harvested_code_for_paper("2110.04722")
get_code_for_paper("2110.04722")
have("2110.04722")

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

curl https://syntology.ai/api/ran/2110.04722.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.04722.svg)](https://syntology.ai/paper/2110.04722)

Connect an agent — have() is free.