SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.06152 · CVPR · 2021

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Ping Luo, Chen Qian, Sheng Jin, Wentao Liu, Jiahang Wang, Weizhong Liu

arXiv · PDF · Open in the Atlas

Code that ran

14 of 25 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 11 failures of our instrument; 11 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/2105.06152.json · badge: /api/ran/2105.06152.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
HRNet/HigherHRNet-Human-Pose-Estimation canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
leoxiaobin/deep-high-resolution-net.pytorch canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
AIprogrammer/AdvMix marked official in Papers with Code
Papers with Code archive
6 ran · 6 no recorded run
vita-epfl/openpifpaf community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
AverageMeter Ran
ran on a synthesized input · constructed an object; no result was computed
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("a605a498a2198a9d")
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, AverageMeter: 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)

# AverageMeter.__init__ takes no parameters beyond self
# AverageMeter.reset() takes no parameters beyond self
# AverageMeter.update(val, n=1) takes val and optional n

# Since AverageMeter is instantiated with no arguments and the class
# just tracks metrics internally, ARGS should be empty dict for __init__
ARGS = {}
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 AverageMeter — 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 AverageMeter 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
Laplace Ran
ran on a synthesized input
vita-epfl/openpifpaf/src/openpifpaf/network/losses/components.py
pointer only (licence: NOASSERTION) · get_code("6c2047eb02f90875")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vita-epfl/openpifpaf (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.

SoftClamp Ran
ran on a synthesized input
vita-epfl/openpifpaf/src/openpifpaf/network/losses/components.py
pointer only (licence: NOASSERTION) · get_code("d948ea963b20bbdc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vita-epfl/openpifpaf (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.

accuracy Ran
ran; our contract draft was wrong, not the code
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("b44324561953846f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 numpy as np

torch.manual_seed(0)

class MockConfig:
    class MODEL:
        IMAGE_SIZE = [64, 64]
        HEATMAP_SIZE = [16, 16]

class MockArgs:
    reg_coord = False

# Create small heatmap outputs: [batch_size=2, num_joints=4, height=8, width=8]
outputs = torch.randn(2, 4, 8, 8, dtype=torch.float32)

# Create small heatmap targets: [batch_size=2, num_joints=4, height=8, width=8]
target = torch.randn(2, 4, 8, 8, dtype=torch.float32)

# Make sure some heatmap values are positive for get_max_preds
outputs = torch.abs(outputs) + 0.1
target = torch.abs(target) + 0.1

cfg = MockConfig()
args = MockArgs()

ARGS = {
    'outputs': outputs,
    'target': target,
    'hm_type': 'gaussian',
    'thr': 0.5,
    'args': None,
    'cfg': None
}
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 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
aggregate_results Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HRNet/HigherHRNet-Human-Pose-Estimation/lib/core/inference.py
code served (permissive licence) · get_code("b2deafbfd7c1f3fc")
How it ran

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

import torch

torch.manual_seed(0)

class MockConfig:
    def __init__(self):
        self.TEST = MockTestConfig()

class MockTestConfig:
    def __init__(self):
        self.SCALE_FACTOR = [1]
        self.PROJECT2IMAGE = False
        self.FLIP_TEST = True

cfg = MockConfig()

scale_factor = 1

final_heatmaps = torch.randn(2, 17, 8, 6)

tags_list = []

heatmaps = [
    torch.randn(2, 17, 8, 6),
    torch.randn(2, 17, 8, 6)
]

tags = [
    torch.randn(2, 17, 4, 3),
    torch.randn(2, 17, 4, 3)
]

ARGS = {
    'cfg': cfg,
    'scale_factor': scale_factor,
    'final_heatmaps': final_heatmaps,
    'tags_list': tags_list,
    'heatmaps': heatmaps,
    'tags': tags
}
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 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
box_to_center_scale Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
leoxiaobin/deep-high-resolution-net.pytorch/demo/inference.py
code served (permissive licence) · get_code("192666724266ef19")
How it ran

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

# Define the arguments for box_to_center_scale
# box: list of tuple with two tuples representing bottom left and top right corners
# model_image_width: int
# model_image_height: int

box = [
    (10.0, 20.0),      # bottom left corner
    (50.0, 80.0)       # top right corner
]

model_image_width = 256
model_image_height = 192

ARGS = {
    "box": box,
    "model_image_width": model_image_width,
    "model_image_height": model_image_height
}
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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
calc_dists Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("b91b38261b03587d")
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 (3, 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 numpy as np

# Construct valid arguments for calc_dists function
# The function expects:
# - preds: array of shape (batch, channels, 2) with predicted coordinates
# - target: array of shape (batch, channels, 2) with target coordinates
# - normalize: array of shape (batch,) with normalization factors

batch_size = 2
num_channels = 3

# Create preds: (batch=2, channels=3, coords=2)
preds = np.random.rand(batch_size, num_channels, 2).astype(np.float32) * 100

# Create target: (batch=2, channels=3, coords=2)
# Use values > 1 to satisfy the condition in the function
target = np.random.rand(batch_size, num_channels, 2).astype(np.float32) * 100 + 2

# Create normalize: (batch=2,) with positive values for normalization
normalize = np.array([10.0, 15.0], dtype=np.float32)

ARGS = {
    'preds': preds,
    'target': target,
    'normalize': normalize
}
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 (3, 2) — shape (3, 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
HRNet/HigherHRNet-Human-Pose-Estimation/lib/models/pose_higher_hrnet.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.

dist_acc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("1c2da88027e6e151")
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 float64, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a sample distance array with some valid values and some -1 values
# The function expects an array where -1 indicates "ignore this value"
dists = np.array([0.2, 0.6, -1, 0.3, 0.8, -1, 0.1, 0.4])

# Create arguments dictionary
ARGS = {
    "dists": dists,
    "thr": 0.5
}
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 float64, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_max_preds Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
leoxiaobin/deep-high-resolution-net.pytorch/lib/core/inference.py
code served (permissive licence) · get_code("55c58ef5f795e3d1")
How it ran

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

import numpy as np

# Create a small batch of heatmaps
# Shape: (batch_size, num_joints, height, width)
batch_size = 2
num_joints = 3
height = 4
width = 5

# Create realistic heatmap data with values between 0 and 1
np.random.seed(0)
batch_heatmaps = np.random.rand(batch_size, num_joints, height, width).astype(np.float32)

ARGS = {
    'batch_heatmaps': batch_heatmaps
}
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 tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_person_detection_boxes Ran
ran; our contract draft was wrong, not the code
leoxiaobin/deep-high-resolution-net.pytorch/demo/inference.py
code served (permissive licence) · get_code("74bb768e238398b0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 numpy as np
from PIL import Image

torch.manual_seed(0)

class MockDetectionModel(nn.Module):
    """Mock object detection model that returns person detections"""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(1, 1)
    
    def forward(self, images):
        """
        Args:
            images: list of tensors
        Returns:
            list of dicts with 'labels', 'boxes', 'scores' keys
        """
        batch_size = len(images)
        # Return a list with one dict (model expects batch of 1)
        return [{
            'labels': torch.tensor([1, 1, 0], dtype=torch.int64),  # person, person, background
            'boxes': torch.tensor([
                [10.0, 20.0, 100.0, 200.0],
                [50.0, 60.0, 150.0, 250.0],
                [200.0, 300.0, 400.0, 500.0]
            ], dtype=torch.float32),
            'scores': torch.tensor([0.95, 0.65, 0.3], dtype=torch.float32)
        }]

# Create a minimal RGB image (numpy array)
img = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)

# Instantiate mock model
model = MockDetectionModel()

ARGS = {
    'model': model,
    'img': img,
    'threshold': 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, 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
make_input Ran
ran; our contract draft was wrong, not the code
HRNet/HigherHRNet-Human-Pose-Estimation/lib/core/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from ayh015-dev/da-llpose, is pointer only (licence: NONE) · get_code("cdea90667046c71c")
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 ayh015-dev/da-llpose, 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.

tensor2im Ran
ran; our contract draft was wrong, not the code
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("dfdeea3ebb13fa9a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a test tensor with shape (3, 4, 5) - 3 channels, 4 height, 5 width
# Values in range [0, 1] as typically expected for normalized images
test_tensor = torch.rand(3, 4, 5)

ARGS = {
    "input_image": test_tensor,
    "imtype": np.uint8
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
tofloat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("599ce919c4b5d898")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Test case 1: numpy array input
numpy_array = np.array([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

# Test case 2: torch float64 tensor
float64_tensor = torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=torch.float64)

# Test case 3: torch float32 tensor (already correct dtype)
float32_tensor = torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=torch.float32)

# The function takes a single parameter 'x' and returns converted tensor
# We'll test with the float64 tensor as the primary case
ARGS = {
    "x": float64_tensor
}
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 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
build_dataset Not yet run
unverified (harvested, no recorded run)
HRNet/HigherHRNet-Human-Pose-Estimation/lib/dataset/build.py
code served (permissive licence) · get_code("0ff31375e05cb70d")
How it ran

no invocation recorded.

get_pose_net Not yet run
unverified (harvested, no recorded run)
leoxiaobin/deep-high-resolution-net.pytorch/lib/models/pose_hrnet.py
code served (permissive licence) · get_code("2534c81208f21998")
How it ran

no invocation recorded.

get_pose_net Not yet run
unverified (harvested, no recorded run)
HRNet/HigherHRNet-Human-Pose-Estimation/lib/models/pose_higher_hrnet.py
code served (permissive licence) · get_code("b1587fcc78f6fa72")
How it ran

no invocation recorded.

inv_coord_norm Not yet run
unverified (harvested, no recorded run)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("73cacfdb88d0d0fb")
How it ran

no invocation recorded.

make_dataloader Not yet run
unverified (harvested, no recorded run)
HRNet/HigherHRNet-Human-Pose-Estimation/lib/dataset/build.py
code served (permissive licence) · get_code("df9c22deab975625")
How it ran

no invocation recorded.

make_test_dataloader Not yet run
unverified (harvested, no recorded run)
HRNet/HigherHRNet-Human-Pose-Estimation/lib/dataset/build.py
code served (permissive licence) · get_code("a4025bf00b852a33")
How it ran

no invocation recorded.

save_batch_heatmaps Not yet run
unverified (harvested, no recorded run)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("140dbadc1db1bd99")
How it ran

no invocation recorded.

save_batch_image_with_joints Not yet run
unverified (harvested, no recorded run)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("ee768f095e08626d")
How it ran

no invocation recorded.

save_debug_images Not yet run
unverified (harvested, no recorded run)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("98ce27ca4d149960")
How it ran

no invocation recorded.

set_require_grad Not yet run
unverified (harvested, no recorded run)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("1a2ff0244d9cdfcf")
How it ran

no invocation recorded.

train_advmix Not yet run
unverified (harvested, no recorded run)
AIprogrammer/AdvMix/lib/core/function.py
code served (permissive licence) · get_code("a63f8ab8d7310adb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 14 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 1 the same month, 8 later) and 11 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
305 dated earlier, 6 the same month, 369 later, 6 same year, order not determinable · 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
get_max_preds
brick of this paper's assembly: helper
6 other papers
4 dated earlier, 2 later
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
1908.11542 (2019-08)
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
and 3 more not named here
calc_dists
brick of this paper's assembly: helper
5 other papers
4 dated earlier, 1 later
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
1908.11542 (2019-08)
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
and 2 more not named here
dist_acc
brick of this paper's assembly: helper
5 other papers
4 dated earlier, 1 later
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
1908.11542 (2019-08)
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
and 2 more not named here
get_pose_net 5 other papers
4 dated earlier, 1 later
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1904.04514 (2019-04)
High-Resolution Representations for Labeling Pixels and Regions
1908.07919 (2019-08)
Deep High-Resolution Representation Learning for Visual Recognition
and 2 more not named here
box_to_center_scale 2 other papers
1 dated earlier, 1 later
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
2602.03157 (2026-02)
Human-in-the-loop adaptation in group activity feature learning for team sports video retrieval
make_input 2 other papers
1 dated earlier, 1 later
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
2407.15451 (2024-07)
Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions
AverageMeter
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2507.22438 (2025-07)
From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras
aggregate_results 1 other paper
1 dated earlier
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
build_dataset 1 other paper
1 dated earlier
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
get_person_detection_boxes 1 other paper
1 dated earlier
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
get_pose_net 1 other paper
1 dated earlier
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
make_dataloader 1 other paper
1 dated earlier
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
make_test_dataloader 1 other paper
1 dated earlier
1908.10357 (2019-08)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

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

Human pose estimation is a fundamental yet challenging task in computer vision, which aims at localizing human anatomical keypoints. However, unlike human vision that is robust to various data corruptions such as blur and pixelation, current pose estimators are easily confused by these corruptions. This work comprehensively studies and addresses this problem by building rigorous robust benchmarks, termed COCO-C, MPII-C, and OCHuman-C, to evaluate the weaknesses of current advanced pose estimators, and a new algorithm termed AdvMix is proposed to improve their robustness in different corruptions. Our work has several unique benefits. (1) AdvMix is model-agnostic and capable in a wide-spectrum of pose estimation models. (2) AdvMix consists of adversarial augmentation and knowledge distillation. Adversarial augmentation contains two neural network modules that are trained jointly and competitively in an adversarial manner, where a generator network mixes different corrupted images to confuse a pose estimator, improving the robustness of the pose estimator by learning from harder samples. To compensate for the noise patterns by adversarial augmentation, knowledge distillation is applied to transfer clean pose structure knowledge to the target pose estimator. ( 3) Extensive experiments show that AdvMix significantly increases the robustness of pose estimations across a wide range of corruptions, while maintaining accuracy on clean data in various challenging benchmark datasets.

For agents

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

get_harvested_code_for_paper("2105.06152")
get_code_for_paper("2105.06152")
have("2105.06152")

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

curl https://syntology.ai/api/ran/2105.06152.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.06152.svg)](https://syntology.ai/paper/2105.06152)

Connect an agent — have() is free.