SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.07797 · 2021

Conditional Directed Graph Convolution for 3D Human Pose Estimation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2107.07797.json · badge: /api/ran/2107.07797.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
tamasino52/U-CondDGCN reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
import_cpn_poses Ran
ran, honoured the contract we drafted
tamasino52/U-CondDGCN/dataset/data_utils.py
code served (permissive licence) · get_code("bc1023596f74a55e")
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 float, shape (2, 4, 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
import tempfile
import os

# Create a temporary .npz file with the expected structure
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "test_poses.npz")

# Create keypoints array with shape (batch=2, num_keypoints=4, features=3)
# The function returns [:, :, :2], so we need at least 2 feature dimensions
# We use 3 to make it distinct
keypoints = np.random.rand(2, 4, 3).astype(np.float32)

# Save to npz file
np.savez(temp_path, keypoints=keypoints)

ARGS = {
    "path": temp_path
}
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 3, dtype family float, shape (2, 4, 2) — shape (2, 4, 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
suggest_metadata Ran
ran; our contract draft was wrong, not the code
tamasino52/U-CondDGCN/dataset/data_utils.py
code served (permissive licence) · get_code("56891f0e63a3c661")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Define the metadata dictionaries (copied from the function definition)
mpii_metadata = {'layout_name': 'mpii', 'num_joints': 16, 'keypoints_symmetry': [[3, 4, 5, 13, 14, 15], [0, 1, 2, 10, 11, 12]]}

coco_metadata = {'layout_name': 'coco', 'num_joints': 17, 'keypoints_symmetry': [[1, 3, 5, 7, 9, 11, 13, 15], [2, 4, 6, 8, 10, 12, 14, 16]]}

h36m_metadata = {'layout_name': 'h36m', 'num_joints': 17, 'keypoints_symmetry': [[4, 5, 6, 11, 12, 13], [1, 2, 3, 14, 15, 16]]}

humaneva15_metadata = {'layout_name': 'humaneva15', 'num_joints': 15, 'keypoints_symmetry': [[2, 3, 4, 8, 9, 10], [5, 6, 7, 11, 12, 13]]}

humaneva20_metadata = {'layout_name': 'humaneva20', 'num_joints': 20, 'keypoints_symmetry': [[3, 4, 5, 6, 11, 12, 13, 14], [7, 8, 9, 10, 15, 16, 17, 18]]}

def suggest_metadata(name):
    names = []
    for metadata in [mpii_metadata, coco_metadata, h36m_metadata, humaneva15_metadata, humaneva20_metadata]:
        if metadata['layout_name'] in name:
            return metadata
        names.append(metadata['layout_name'])
    raise KeyError('Cannot infer keypoint layout from name "{}". Tried {}.'.format(name, names))

# Test cases for the function - construct valid arguments
ARGS = {
    'name': 'coco_dataset'
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
import_detectron_poses Not yet run
unverified (harvested, no recorded run)
tamasino52/U-CondDGCN/dataset/data_utils.py
code served (permissive licence) · get_code("485aa6accecbf825")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
import_cpn_poses 1 other paper
1 dated earlier
2004.13985 (2020-04)
Motion Guided 3D Pose Estimation from Videos
import_detectron_poses 1 other paper
1 dated earlier
2004.13985 (2020-04)
Motion Guided 3D Pose Estimation from Videos
suggest_metadata 1 other paper
1 dated earlier
2004.13985 (2020-04)
Motion Guided 3D Pose Estimation from Videos

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

Graph convolutional networks have significantly improved 3D human pose estimation by representing the human skeleton as an undirected graph. However, this representation fails to reflect the articulated characteristic of human skeletons as the hierarchical orders among the joints are not explicitly presented. In this paper, we propose to represent the human skeleton as a directed graph with the joints as nodes and bones as edges that are directed from parent joints to child joints. By so doing, the directions of edges can explicitly reflect the hierarchical relationships among the nodes. Based on this representation, we further propose a spatial-temporal conditional directed graph convolution to leverage varying non-local dependence for different poses by conditioning the graph topology on input poses. Altogether, we form a U-shaped network, named U-shaped Conditional Directed Graph Convolutional Network, for 3D human pose estimation from monocular videos. To evaluate the effectiveness of our method, we conducted extensive experiments on two challenging large-scale benchmarks: Human3.6M and MPI-INF-3DHP. Both quantitative and qualitative results show that our method achieves top performance. Also, ablation studies show that directed graphs can better exploit the hierarchy of articulated human skeletons than undirected graphs, and the conditional connections can yield adaptive graph topologies for different poses.

For agents

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

get_harvested_code_for_paper("2107.07797")
get_code_for_paper("2107.07797")
have("2107.07797")

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

curl https://syntology.ai/api/ran/2107.07797.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.07797.svg)](https://syntology.ai/paper/2107.07797)

Connect an agent — have() is free.