SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.03345 · 2019

Semantic Graph Convolutional Networks for 3D Human Pose Regression

arXiv · PDF · Open in the Atlas

Code that ran

3 of 8 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 1 has no contract verdict; 2 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/1904.03345.json · badge: /api/ran/1904.03345.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
garyzhao/SemGCN canonical (classifier label)
classifier basis: census
3 ran · 5 no recorded run
FunctionStatusWhere it lives
fetch Ran
ran on a synthesized input
garyzhao/SemGCN/common/data_utils.py
code served (permissive licence) · get_code("a01e37bb132ecaf4")
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
import numpy as np

torch.manual_seed(0)

# Build keypoints structure: dict[subject][action] = list of 2D pose arrays
keypoints = {
    'S1': {
        'walking 0': [np.random.randn(10, 17, 2), np.random.randn(8, 17, 2)],
        'sitting 1': [np.random.randn(12, 17, 2), np.random.randn(9, 17, 2)],
    },
    'S2': {
        'walking 0': [np.random.randn(7, 17, 2), np.random.randn(6, 17, 2)],
        'running 2': [np.random.randn(5, 17, 2), np.random.randn(4, 17, 2)],
    }
}

# Build dataset structure: dict[subject][action] = dict with 'positions_3d'
dataset = {
    'S1': {
        'walking 0': {
            'positions_3d': [np.random.randn(10, 17, 3), np.random.randn(8, 17, 3)]
        },
        'sitting 1': {
            'positions_3d': [np.random.randn(12, 17, 3), np.random.randn(9, 17, 3)]
        },
    },
    'S2': {
        'walking 0': {
            'positions_3d': [np.random.randn(7, 17, 3), np.random.randn(6, 17, 3)]
        },
        'running 2': {
            'positions_3d': [np.random.randn(5, 17, 3), np.random.randn(4, 17, 3)]
        },
    }
}

ARGS = {
    'subjects': ['S1', 'S2'],
    'dataset': dataset,
    'keypoints': keypoints,
    'action_filter': ['walking', 'sitting'],
    'stride': 2,
    'parse_3d_poses': True,
}
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
mpjpe Ran
ran; our contract draft was wrong, not the code
garyzhao/SemGCN/common/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from davidpengucf/DAF-DG, is pointer only (licence: NONE) · get_code("3afb541a8147d123")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from davidpengucf/DAF-DG, 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.

p_mpjpe Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
garyzhao/SemGCN/common/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from JihuaPeng/KTPFormer, is pointer only (licence: NONE) · get_code("29d56deadc8fcd3c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JihuaPeng/KTPFormer, 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.

create_2d_data Not yet run
unverified (harvested, no recorded run)
garyzhao/SemGCN/common/data_utils.py
code served (permissive licence) · get_code("c1285546d25a021d")
How it ran

no invocation recorded.

image_coordinates Not yet run
unverified (harvested, no recorded run)
garyzhao/SemGCN/common/camera.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from JihuaPeng/KTPFormer, is pointer only (licence: NONE) · get_code("7669d6b1ce1e7096")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JihuaPeng/KTPFormer, 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. No invocation recorded.

normalize_screen_coordinates Not yet run
unverified (harvested, no recorded run)
garyzhao/SemGCN/common/camera.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from JihuaPeng/KTPFormer, is pointer only (licence: NONE) · get_code("82baf6aa4fb040a1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JihuaPeng/KTPFormer, 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. No invocation recorded.

read_3d_data Not yet run
unverified (harvested, no recorded run)
garyzhao/SemGCN/common/data_utils.py
code served (permissive licence) · get_code("2bc24c0c1c934d2d")
How it ran

no invocation recorded.

weighted_mpjpe Not yet run
unverified (harvested, no recorded run)
garyzhao/SemGCN/common/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from davidpengucf/DAF-DG, is pointer only (licence: NONE) · get_code("6dd3ba892d9349d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from davidpengucf/DAF-DG, 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. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 3 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
normalize_screen_coordinates 10 other papers
10 later
2004.13985 (2020-04)
Motion Guided 3D Pose Estimation from Videos
2103.14304 (2021-03)
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
2111.12707 (2021-11)
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
and 7 more not named here
image_coordinates 4 other papers
4 later
2210.06110 (2022-10)
Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers
2211.16940 (2022-11)
DiffPose: Toward More Reliable 3D Pose Estimation
2403.11310 (2024-03)
A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation
and 1 more not named here
mpjpe 4 other papers
4 later
2007.09389 (2020-07)
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach
2211.16940 (2022-11)
DiffPose: Toward More Reliable 3D Pose Estimation
2308.10436 (2023-08)
Approximately Equivariant Graph Networks
and 1 more not named here
p_mpjpe 3 other papers
3 later
2211.16940 (2022-11)
DiffPose: Toward More Reliable 3D Pose Estimation
2308.10436 (2023-08)
Approximately Equivariant Graph Networks
2404.00658 (2024-04)
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation
weighted_mpjpe 3 other papers
3 later
2211.16940 (2022-11)
DiffPose: Toward More Reliable 3D Pose Estimation
2308.10436 (2023-08)
Approximately Equivariant Graph Networks
2403.11310 (2024-03)
A Dual-Augmentor Framework for Domain Generalization in 3D 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters.

For agents

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

get_harvested_code_for_paper("1904.03345")
get_code_for_paper("1904.03345")
have("1904.03345")

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

curl https://syntology.ai/api/ran/1904.03345.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.03345.svg)](https://syntology.ai/paper/1904.03345)

Connect an agent — have() is free.