SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_16202 · AAAI · 2021

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

Bo Yang, Yu Cheng, Bo Wang, Robby Tan

Open in the Atlas

Code that ran

3 of 5 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, 1 violated it and 2 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/aaai_16202.json · badge: /api/ran/aaai_16202.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
3dpose/GnTCN canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
load_annot Ran
ran on a synthesized input
3dpose/GnTCN/util/datautil.py
code served (permissive licence) · get_code("3c1ae5c97c6b8e54")
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 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 scipy.io as sio
import numpy as np
import tempfile
import os

# Create a minimal valid .mat file that the function expects
def create_test_mat_file():
    # Create the nested structure that parse_pose expects
    # Each element needs: annot2, annot3, univ_annot3, isValidFrame
    
    num_frames = 2
    num_inst = 3
    
    annotations = np.empty((num_frames, num_inst), dtype=object)
    
    for i in range(num_frames):
        for j in range(num_inst):
            # Create a structured array with the required fields
            frame_data = {}
            
            # annot2: 2D pose annotations
            frame_data['annot2'] = np.random.rand(17, 2).astype(np.float32)
            
            # annot3: 3D pose annotations
            frame_data['annot3'] = np.random.rand(17, 3).astype(np.float32)
            
            # univ_annot3: universal 3D annotations
            frame_data['univ_annot3'] = np.random.rand(17, 3).astype(np.float32)
            
            # isValidFrame: validity flag (needs to be wrapped in nested arrays)
            frame_data['isValidFrame'] = np.array([[np.array([[1]], dtype=bool)]])
            
            annotations[i, j] = frame_data
    
    # Create temporary .mat file
    temp_dir = tempfile.gettempdir()
    temp_file = os.path.join(temp_dir, 'test_annotations.mat')
    
    sio.savemat(temp_file, {'annotations': annotations})
    return temp_file

# Generate the test file
test_mat_file = create_test_mat_file()

ARGS = {
    'fname': test_mat_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, 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
load_occ Ran
ran on a synthesized input
3dpose/GnTCN/util/datautil.py
code served (permissive licence) · get_code("ff838c93a35c408e")
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 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 scipy.io as sio
import numpy as np
import tempfile
import os

# Create a temporary .mat file with the required structure
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_occlusion.mat")

# Create sample occlusion_labels data
# Shape: (num_frames, num_inst) - let's use (3, 2) for distinct dimensions
num_frames = 3
num_inst = 2
occlusion_data = np.random.randint(0, 2, size=(num_frames, num_inst)).astype(np.float32)

# Save to .mat file
sio.savemat(temp_file, {'occlusion_labels': occlusion_data})

ARGS = {
    'fname': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, 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
mean Ran
ran, violated the contract we drafted
3dpose/GnTCN/util/evaluate.py
code served (permissive licence) · get_code("63cf7ec10b164550")
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) and returned float, 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 torch

torch.manual_seed(0)

# The function 'mean' takes a list 'l' and computes sum(l) / len(l)
# It needs a list of numeric values that support addition and division

ARGS = {
    "l": [1, 2, 3, 4, 5]
}
Setup block drafted by
a language model, Claude Haiku 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 float, 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
calculate_multiperson_errors Not yet run
unverified (harvested, no recorded run)
3dpose/GnTCN/util/evaluate.py
code served (permissive licence) · get_code("7b5bfeb50683737a")
How it ran

no invocation recorded.

mpii_compute_3d_pck Not yet run
unverified (harvested, no recorded run)
3dpose/GnTCN/util/evaluate.py
code served (permissive licence) · get_code("e3773672196b82c0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
mean 5 other papers
3 dated earlier, 2 later
1909.13584 (2019-09)
Interpretations are useful: penalizing explanations to align neural networks with prior knowledge
2007.01332 (2020-07)
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
2009.12789 (2020-09)
Learning Optimal Representations with the Decodable Information Bottleneck
and 2 more not named here

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

Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and inaccurate person detection. To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that does not require camera parameters. In particular, we introduce a human-joint GCN, which unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results. We also introduce a human-bone GCN, which models the bone connections and provides more information beyond human joints. The two GCNs work together to estimate the spatial frame-wise 3D poses, and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information. To further refine the 3D pose estimation, we use our temporal convolutional networks (TCNs) to enforce the temporal and human-dynamics constraints. We use a joint-TCN to estimate person-centric 3D poses across frames, and propose a velocity-TCN to estimate the speed of 3D joints to ensure the consistency of the 3D pose estimation in consecutive frames. Finally, to estimate the 3D human poses for multiple persons, we propose a root-TCN that estimates camera-centric 3D poses without requiring camera parameters. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method. Our code and models are available at https://github.com/3dpose/GnTCN.

For agents

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

get_harvested_code_for_paper("aaai_16202")
get_code_for_paper("aaai_16202")
have("aaai_16202")

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

curl https://syntology.ai/api/ran/aaai_16202.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_16202.svg)](https://syntology.ai/paper/aaai_16202)

Connect an agent — have() is free.