SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.03478 · 2019

A Real-time Global Inference Network for One-stage Referring Expression Comprehension

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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 9 have no contract verdict; 4 failures of our instrument; 2 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/1912.03478.json · badge: /api/ran/1912.03478.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
luogen1996/Real-time-Global-Inference-Network canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
add_extras Ran
ran; our contract draft was wrong, not the code
luogen1996/Real-time-Global-Inference-Network/code/ssd_vgg.py
code served (permissive licence) · get_code("2a8545e480332b47")
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 1, 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

torch.manual_seed(0)

# The function expects:
# - cfg: a list/tuple that can contain integers and 'S' strings
# - i: an integer representing initial in_channels
# - batch_norm: a boolean (default False)

# Looking at the function logic:
# - It iterates over cfg with enumerate
# - cfg elements can be 'S' or integers (representing out_channels)
# - When v == 'S', it looks at cfg[k+1] for the next value
# - in_channels starts as i and gets updated to v in each iteration
# - flag alternates between False and True to choose kernel_size (1 or 3)

# A valid cfg would be a list with integers and 'S' markers
# Example: [256, 'S', 512, 128, 'S', 256, 128]
# This means: 
# - First layer: in_channels=i, out_channels=256, kernel_size=1
# - Second layer: in_channels=256, out_channels=512 (from cfg[k+1]), kernel_size=3, stride=2
# - Third layer: in_channels=512, out_channels=128, kernel_size=1
# - Fourth layer: in_channels=128, out_channels=256 (from cfg[k+1]), kernel_size=3, stride=2
# - Fifth layer: in_channels=256, out_channels=128, kernel_size=1

cfg = [256, 'S', 512, 128, 'S', 256, 128]
i = 1024
batch_norm = False

ARGS = {
    'cfg': cfg,
    'i': i,
    'batch_norm': batch_norm
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
conv2d Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/mdl.py
code served (permissive licence) · get_code("4b907a406f06ace0")
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 Conv2d. 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 = {
    "ni": 3,
    "nf": 16,
    "ks": 3,
    "stride": 1,
    "padding": None,
    "bias": 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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv2d_relu Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/mdl.py
code served (permissive licence) · get_code("7af4e486b4c60709")
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 = {
    'ni': 3,
    'nf': 16,
    'ks': 3,
    'stride': 1,
    'padding': None,
    'bn': True,
    'bias': 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 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
luogen1996/Real-time-Global-Inference-Network/code/fpn_resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. 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.

cthw2tlbr Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/anchors.py
code served (permissive licence) · get_code("a7dcff4207ca66bf")
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 2, dtype family float, shape (2, 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)

# The function expects boxes tensor with shape (..., 4)
# where the last dimension contains [center_x, center_y, width, height]
# It performs element-wise operations and concatenation
boxes = torch.randn(2, 4)

ARGS = {
    "boxes": boxes
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
generate_iou_groundtruth Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/dat_loader.py
code served (permissive licence) · get_code("d711974c290e3888")
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 2, dtype family float, shape (10, 8) 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

# The function takes three parameters:
# 1. grid_shapes: widths and heights for generation (w, h) - used as IMAGE_WIDTH and IMAGE_HEIGHT
# 2. true_anchor: anchor's x and y (x, y) - used as t_x, t_y
# 3. true_wh: anchor's width and height (w, h) - used as t_w, t_h

# Looking at the function body:
# - grid_shapes is indexed as [0] and [1], so it's a tuple/list of 2 elements
# - true_anchor is indexed as [0] and [1], so it's a tuple/list of 2 elements
# - true_wh is indexed as [0] and [1], so it's a tuple/list of 2 elements
# - grid_shapes values are used in range() and array creation, so they should be integers
# - true_anchor and true_wh values are used in arithmetic operations

ARGS = {
    "grid_shapes": (10, 8),  # width=10, height=8
    "true_anchor": (5.0, 4.0),  # x=5.0, y=4.0 (center of grid approximately)
    "true_wh": (2.0, 1.5),  # width=2.0, height=1.5
}
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 ndarray, ndim 2, dtype family float, shape (10, 8) — shape (10, 8) 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
multibox Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
luogen1996/Real-time-Global-Inference-Network/code/ssd_vgg.py
code served (permissive licence) · get_code("b490ac8699f5a7ad")
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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# First, we need to create a VGG configuration and build the vgg layers
vgg_cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M', 512, 512, 512]

def vgg(cfg, i, batch_norm=False):
    layers = []
    in_channels = i
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        elif v == 'C':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    pool5 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
    conv6 = nn.Conv2d(512, 1024, kernel_size=3, padding=6, dilation=6)
    conv7 = nn.Conv2d(1024, 1024, kernel_size=1)
    layers += [pool5, conv6, nn.ReLU(inplace=True), conv7, nn.ReLU(inplace=True)]
    return layers

# Build vgg layers
vgg_layers = vgg(vgg_cfg, 3, batch_norm=False)

# Create extra_layers - these should be conv layers with out_channels attribute
# The function accesses extra_layers[1::2] (every other element starting from index 1)
# and expects them to have .out_channels
extra_layers = [
    nn.Conv2d(1024, 256, kernel_size=1),
    nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
    nn.Conv2d(512, 128, kernel_size=1),
    nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
]

# cfg is a list of numbers representing the number of boxes per feature map
# The function expects len(cfg) >= 2 + len(extra_layers[1::2])
# extra_layers[1::2] has length 2, so cfg needs at least 4 elements
cfg = [4, 6, 6, 4]

# num_classes
num_classes = 21

ARGS = {
    'vgg': vgg_layers,
    'extra_layers': extra_layers,
    'cfg': cfg,
    'num_classes': num_classes
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — 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
pad_out Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/fpn_resnet.py
code served (permissive licence) · get_code("ad11ef6d39eb2ff3")
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 int, ndim 0, dtype family int, 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 torch
import numpy as np

torch.manual_seed(0)

# The function pad_out takes a single parameter k (kernel size)
# and returns padding needed for same-size convolution
# k should be an integer

k = 3

ARGS = {
    "k": k
}
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 int, ndim 0, dtype family int, 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
pil2tensor Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/dat_loader.py
code served (permissive licence) · get_code("dfeaf11b09c7a0bc")
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 3, dtype family float, shape (2, 3, 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 numpy as np
import torch

torch.manual_seed(0)

# Create a PIL-style image array (height, width, channels)
# Using small distinct dimensions: height=3, width=4, channels=2
image_array = np.random.randint(0, 256, size=(3, 4, 2), dtype=np.uint8)

ARGS = {
    "image": image_array,
    "dtype": np.float32,
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
reshape Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/evaluator.py
code served (permissive licence) · get_code("fdb481756a08ea1e")
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 2, dtype family float, shape (2, 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)

# Create a box tensor of shape (N, 4) in y1x1y2x2 format
# N=2 for batch size, 4 for the coordinates
box = torch.tensor([
    [0.1, 0.2, 0.5, 0.6],
    [0.3, 0.4, 0.7, 0.8]
], dtype=torch.float32)

# Create new_size tensor of shape (N, 2) with (h, w) pairs
# N=2 to match box batch size, 2 for height and width
new_size = torch.tensor([
    [100.0, 200.0],
    [150.0, 250.0]
], dtype=torch.float32)

ARGS = {
    "box": box,
    "new_size": new_size
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
tlbr2cthw Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/anchors.py
code served (permissive licence) · get_code("345cb82041ecd304")
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 2, dtype family float, shape (2, 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)

# The function expects boxes in top/left bottom/right format
# Shape: (..., 4) where last dimension is [top, left, bottom, right]
# We'll create a batch of 2 boxes with 4 coordinates each
boxes = torch.tensor([
    [1.0, 2.0, 5.0, 8.0],  # box 1: top=1, left=2, bottom=5, right=8
    [0.5, 1.5, 4.0, 6.5]   # box 2: top=0.5, left=1.5, bottom=4, right=6.5
])

ARGS = {
    "boxes": boxes
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
tlbr2tlhw Ran
ran on a synthesized input
luogen1996/Real-time-Global-Inference-Network/code/anchors.py
code served (permissive licence) · get_code("6206186edff240f5")
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 2, dtype family float, shape (2, 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)

# Create a tensor of bounding boxes in top-left, bottom-right format
# Shape: (batch_size=2, coordinates=4)
# Each row is [top, left, bottom, right]
boxes = torch.tensor([
    [10.0, 20.0, 50.0, 80.0],
    [5.0, 15.0, 45.0, 75.0]
], dtype=torch.float32)

ARGS = {
    'boxes': boxes
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
vgg Ran
ran; our contract draft was wrong, not the code
luogen1996/Real-time-Global-Inference-Network/code/ssd_vgg.py
code served (permissive licence) · get_code("6921f7ed00595a4f")
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 1, 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

torch.manual_seed(0)

# The function expects:
# - cfg: a list/tuple containing integers (number of channels) and strings 'M' or 'C' for pooling
# - i: integer representing input channels
# - batch_norm: boolean flag

# Looking at the function body, cfg is iterated over and can contain:
# - 'M' or 'C' for MaxPool2d layers
# - integers for Conv2d output channels
# The function builds a VGG-style network

# Create a simple configuration
cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M', 512, 512, 512]

# Input channels (typically 3 for RGB images)
i = 3

# Batch normalization flag
batch_norm = False

ARGS = {
    'cfg': cfg,
    'i': i,
    'batch_norm': batch_norm
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
collater Not yet run
unverified (harvested, no recorded run)
luogen1996/Real-time-Global-Inference-Network/code/dat_loader.py
code served (permissive licence) · get_code("13ae5809344e4f05")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
luogen1996/Real-time-Global-Inference-Network/code/fpn_resnet.py
code served (permissive licence) · get_code("fe0212a6c494a57f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 2 the same month, 4 later) and 1 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
conv3x3 686 other papers
178 dated earlier, 3 the same month, 505 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
vgg 11 other papers
7 dated earlier, 1 the same month, 3 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1611.08563 (2016-11)
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
and 8 more not named here
add_extras 6 other papers
5 dated earlier, 1 later
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1611.08563 (2016-11)
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
1901.02446 (2019-01)
Panoptic Feature Pyramid Networks
and 3 more not named here
multibox 6 other papers
3 dated earlier, 3 later
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
1911.10033 (2019-11)
Domain Adaptation for Object Detection via Style Consistency
and 3 more not named here
collater 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
conv2d 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
conv2d_relu 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
cthw2tlbr 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
pad_out 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
pil2tensor 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
reshape 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
resnet50 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
tlbr2cthw 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
tlbr2tlhw 1 other paper
1 dated earlier
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries

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

Referring Expression Comprehension (REC) is an emerging research spot in computer vision, which refers to detecting the target region in an image given an text description. Most existing REC methods follow a multi-stage pipeline, which are computationally expensive and greatly limit the application of REC. In this paper, we propose a one-stage model towards real-time REC, termed Real-time Global Inference Network (RealGIN). RealGIN addresses the diversity and complexity issues in REC with two innovative designs: the Adaptive Feature Selection (AFS) and the Global Attentive ReAsoNing unit (GARAN). AFS adaptively fuses features at different semantic levels to handle the varying content of expressions. GARAN uses the textual feature as a pivot to collect expression-related visual information from all regions, and thenselectively diffuse such information back to all regions, which provides sufficient context for modeling the complex linguistic conditions in expressions. On five benchmark datasets, i.e., RefCOCO, RefCOCO+, RefCOCOg, ReferIt and Flickr30k, the proposed RealGIN outperforms most prior works and achieves very competitive performances against the most advanced method, i.e., MAttNet. Most importantly, under the same hardware, RealGIN can boost the processing speed by about 10 times over the existing methods.

For agents

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

get_harvested_code_for_paper("1912.03478")
get_code_for_paper("1912.03478")
have("1912.03478")

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

curl https://syntology.ai/api/ran/1912.03478.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.03478.svg)](https://syntology.ai/paper/1912.03478)

Connect an agent — have() is free.