SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.09826 · IJCAI · 2022

SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification

Chunyan Miao, Haocong Rao

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 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 5 have no contract verdict; 1 failure of our instrument; 5 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/2204.09826.json · badge: /api/ran/2204.09826.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
Kali-Hac/SimMC canonical (classifier label)
classifier basis not recorded on the link
6 ran · 5 no recorded run
FunctionStatusWhere it lives
k_reciprocal_neigh Ran
ran on a synthesized input
Kali-Hac/SimMC/utils/faiss_rerank.py
code served (permissive licence) · get_code("a610e67edff490e6")
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 1, dtype family int, shape (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 numpy as np

# Create a small initial_rank matrix
# The function indexes into this with [i, :k1+1] and [forward_k_neigh_index, :k1+1]
# So we need enough rows and columns
initial_rank = np.array([
    [0, 1, 2, 3, 4],
    [1, 0, 3, 2, 4],
    [2, 3, 0, 1, 4],
    [3, 2, 1, 0, 4],
    [4, 0, 1, 2, 3]
], dtype=np.int64)

# i is an index into the first dimension of initial_rank
i = 0

# k1 is used to slice the rank matrix up to k1+1
k1 = 2

ARGS = {
    "initial_rank": initial_rank,
    "i": i,
    "k1": k1
}
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 1, dtype family int, shape (3,) — shape (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
reduce2body Ran
ran on a synthesized input
Kali-Hac/SimMC/utils/process_L3.py
code served (permissive licence) · get_code("677c3e6b941ea5a3")
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 4, dtype family float, shape (2, 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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create a sample input tensor X
# Shape: (batch_size, time_steps, num_joints, coordinates)
# For joint_num=20, we need 20 joints, each with 3 coordinates (x, y, z)
batch_size = 2
time_steps = 4
num_joints = 20
coordinates = 3

X = np.random.randn(batch_size, time_steps, num_joints, coordinates).astype(np.float32)

# Define ARGS with all parameters
ARGS = {
    "X": X,
    "joint_num": 20
}
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 4, dtype family float, shape (2, 4, 5, 3) — shape (2, 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
reduce2body Ran
ran on a synthesized input
Kali-Hac/SimMC/utils/process_cme_L3.py
code served (permissive licence) · get_code("2f9cbec400e7f8fc")
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 4, dtype family float, shape (2, 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 numpy as np

# The function reduce2body expects:
# - X: a numpy array of shape (batch_size, sequence_length, num_joints, coordinates)
# - joint_num: an integer specifying the skeleton format (default 20)

# Create a small test input array
# Shape: (batch=2, sequence=4, joints=20, coords=3)
np.random.seed(0)
X = np.random.randn(2, 4, 20, 3).astype(np.float32)

ARGS = {
    "X": X,
    "joint_num": 20
}
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 4, dtype family float, shape (2, 4, 5, 3) — shape (2, 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
reduce2part Ran
ran on a synthesized input
Kali-Hac/SimMC/utils/process_L3.py
code served (permissive licence) · get_code("8afab386b1dcf86d")
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 4, dtype family float, shape (2, 4, 10, 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 numpy as np

# Create a small test input
# X shape should be [batch_size, time_steps, joint_num, coordinates]
# For joint_num=20, we need 20 joints with 3 coordinates each
batch_size = 2
time_steps = 4
joint_num = 20
coordinates = 3

X = np.random.randn(batch_size, time_steps, joint_num, coordinates).astype(np.float32)

ARGS = {
    "X": X,
    "joint_num": 20
}
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 4, dtype family float, shape (2, 4, 10, 3) — shape (2, 4, 10, 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
reduce2part Ran
ran on a synthesized input
Kali-Hac/SimMC/utils/process_cme_L3.py
code served (permissive licence) · get_code("1be88827c6eae5df")
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 4, dtype family float, shape (2, 3, 10, 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 numpy as np

# Create a small dummy input array
# The function expects X with shape [batch_size, time_steps, num_joints, coordinates]
# For joint_num=20, we need at least 20 joints
# Let's create: batch_size=2, time_steps=3, num_joints=20, coordinates=3
batch_size = 2
time_steps = 3
num_joints = 20
coordinates = 3

X = np.random.randn(batch_size, time_steps, num_joints, coordinates).astype(np.float32)

ARGS = {
    "X": X,
    "joint_num": 20
}
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 4, dtype family float, shape (2, 3, 10, 3) — shape (2, 3, 10, 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
swig_ptr_from_FloatTensor Ran
ran; our contract draft was wrong, not the code
Kali-Hac/SimMC/utils/faiss_utils.py
code served (permissive licence) · get_code("f295b8050ce2a4f1")
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 SwigPyObject. 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 faiss

torch.manual_seed(0)

# Create a small contiguous float32 tensor
x = torch.randn(2, 4, dtype=torch.float32).contiguous()

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
faiss, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SwigPyObject — a SwigPyObject output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SwigPyObject 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
compute_jaccard_distance Not yet run
unverified (harvested, no recorded run)
Kali-Hac/SimMC/utils/faiss_rerank.py
code served (permissive licence) · get_code("b6548c531f96defb")
How it ran

no invocation recorded.

gen_train_data Not yet run
unverified (harvested, no recorded run)
Kali-Hac/SimMC/utils/process_L3.py
code served (permissive licence) · get_code("37fb86d5da762cea")
How it ran

no invocation recorded.

gen_train_data Not yet run
unverified (harvested, no recorded run)
Kali-Hac/SimMC/utils/process_cme_L3.py
code served (permissive licence) · get_code("4023b8fa8809a1ef")
How it ran

no invocation recorded.

search_index_pytorch Not yet run
unverified (harvested, no recorded run)
Kali-Hac/SimMC/utils/faiss_utils.py
code served (permissive licence) · get_code("78ca4879f13cc9d5")
How it ran

no invocation recorded.

swig_ptr_from_LongTensor Not yet run
unverified (harvested, no recorded run)
Kali-Hac/SimMC/utils/faiss_utils.py
code served (permissive licence) · get_code("892aeccb03c9a237")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 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
k_reciprocal_neigh 5 other papers
5 dated earlier
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
1805.09501 (2018-05)
AutoAugment: Learning Augmentation Policies from Data
1811.07130 (2018-11)
Batch DropBlock Network for Person Re-identification and Beyond
and 2 more not named here
swig_ptr_from_FloatTensor 4 other papers
3 dated earlier, 1 same year, order not determinable
1805.09501 (2018-05)
AutoAugment: Learning Augmentation Policies from Data
1911.02116 (2019-11)
Unsupervised Cross-lingual Representation Learning at Scale
2004.10566 (2020-04)
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
and 1 more not named here
swig_ptr_from_LongTensor 4 other papers
3 dated earlier, 1 same year, order not determinable
1805.09501 (2018-05)
AutoAugment: Learning Augmentation Policies from Data
1911.02116 (2019-11)
Unsupervised Cross-lingual Representation Learning at Scale
2004.10566 (2020-04)
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
and 1 more not named here
search_index_pytorch 3 other papers
2 dated earlier, 1 same year, order not determinable
1805.09501 (2018-05)
AutoAugment: Learning Augmentation Policies from Data
2004.10566 (2020-04)
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
aaai_19970 (2022 (year only))
SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-identification
reduce2body 1 other paper
1 later
2303.06819 (2023-03)
TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification
reduce2body 1 other paper
1 later
2303.06819 (2023-03)
TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification
reduce2part 1 other paper
1 later
2303.06819 (2023-03)
TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification
reduce2part 1 other paper
1 later
2303.06819 (2023-03)
TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification

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

Recent advances in skeleton-based person reidentification (re-ID) obtain impressive performance via either hand-crafted skeleton descriptors or skeleton representation learning with deep learning paradigms. However, they typically require skeletal pre-modeling and label information for training, which leads to limited applicability of these methods. In this paper, we focus on unsupervised skeleton-based person re-ID, and present a generic Simple Masked Contrastive learning (SimMC) framework to learn effective representations from unlabeled 3D skeletons for person re-ID. Specifically, to fully exploit skeleton features within each skeleton sequence, we first devise a masked prototype contrastive learning (MPC) scheme to cluster the most typical skeleton features (skeleton prototypes) from different subsequences randomly masked from raw sequences, and contrast the inherent similarity between skeleton features and different prototypes to learn discriminative skeleton representations without using any label. Then, considering that different subsequences within the same sequence usually enjoy strong correlations due to the nature of motion continuity, we propose the masked intra-sequence contrastive learning (MIC) to capture intra-sequence pattern consistency between subsequences, so as to encourage learning more effective skeleton representations for person re-ID. Extensive experiments validate that the proposed SimMC outperforms most state-of-the-art skeleton-based methods. We further show its scalability and efficiency in enhancing the performance of existing models. Our codes are available at https://github.com/Kali-Hac/SimMC.

For agents

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

get_harvested_code_for_paper("2204.09826")
get_code_for_paper("2204.09826")
have("2204.09826")

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

curl https://syntology.ai/api/ran/2204.09826.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.09826.svg)](https://syntology.ai/paper/2204.09826)

Connect an agent — have() is free.