SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.06551 · 2022

MotionBERT: A Unified Perspective on Learning Human Motion Representations

arXiv · PDF · Open in the Atlas

Code that ran

8 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 3 have no contract verdict; 5 failures of our instrument; 3 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/2210.06551.json · badge: /api/ran/2210.06551.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
Walter0807/MotionBERT canonical (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Walter0807/MotionBERT/lib/model/drop.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from fudan-zvg/SeaFormer, is pointer only (licence: NONE) · get_code("3ac6b7d76e8e3584")
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 fudan-zvg/SeaFormer, 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.

err Ran
ran on a synthesized input
Walter0807/MotionBERT/infer_wild_mesh.py
code served (permissive licence) · get_code("2e29155b32d35c84")
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; 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

# Analyze the function:
# err(p, x, y) computes:
#   p[0] * x + np.array([p[1], p[2], p[3]]) - y
# This means:
#   - p is indexable with [0], [1], [2], [3] → array-like with at least 4 elements
#   - x is multiplied by p[0] → numeric array
#   - The result is broadcasted with [p[1], p[2], p[3]] → suggests last dim is 3
#   - y has same shape as p[0] * x + bias
#   - np.linalg.norm(..., axis=-1) → reduces last axis
#   - .mean() → scalar output

# p: array with 4 elements (p[0] is scalar, p[1:4] form bias)
p = np.array([2.0, 0.5, 1.0, 1.5, 0.2])

# x: shape (batch, features) where features last dim is 3
# Let's use shape (2, 3) for batch of 2, feature dim of 3
x = np.array([[1.0, 2.0, 3.0],
              [4.0, 5.0, 6.0]])

# y: same shape as (p[0] * x + bias)
# p[0] * x has shape (2, 3)
# np.array([p[1], p[2], p[3]]) adds (3,) which broadcasts to (2, 3)
# So y should be (2, 3)
y = np.array([[2.5, 5.0, 7.5],
              [9.0, 11.5, 14.0]])

ARGS = {
    "p": p,
    "x": x,
    "y": y
}
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 — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
extract_feats Ran
ran on a synthesized input
Walter0807/MotionBERT/train_action_1shot.py
code served (permissive licence) · get_code("bd08312c6f24ba04")
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 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

torch.manual_seed(0)

# Define a minimal model that takes batch_input and returns features
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = MinimalModel()

# Create a minimal dataloader as a list of (batch_input, batch_gt) tuples
# Each batch has 2 samples, input dim 4, gt dim 3
dataloader_x = [
    (torch.randn(2, 4), torch.randn(2, 3)),
    (torch.randn(2, 4), torch.randn(2, 3)),
]

ARGS = {
    "dataloader_x": dataloader_x,
    "model": model,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
loss_mpjpe Ran
ran; our contract draft was wrong, not the code
Walter0807/MotionBERT/lib/model/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from fanglaosi/skeleton-in-context, is pointer only (licence: NONE) · get_code("48a788f0938a2209")
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 fanglaosi/skeleton-in-context, 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.

mpjpe Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Walter0807/MotionBERT/lib/model/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from fanglaosi/skeleton-in-context, is pointer only (licence: NONE) · get_code("08fdd93d7a20142f")
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 fanglaosi/skeleton-in-context, 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)
Walter0807/MotionBERT/lib/model/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from fanglaosi/skeleton-in-context, is pointer only (licence: NONE) · get_code("e2b944da85a57144")
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 fanglaosi/skeleton-in-context, 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.

trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Walter0807/MotionBERT/lib/model/DSTformer.py
code served (permissive licence) · get_code("02566da69866c48c")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 math

torch.manual_seed(0)

# Create a small tensor to be filled with truncated normal values
tensor = torch.empty(2, 4)

# Define arguments for trunc_normal_
ARGS = {
    'tensor': tensor,
    'mean': 0.0,
    'std': 1.0,
    'a': -2.0,
    'b': 2.0
}
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 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
validate Ran
ran on a synthesized input
Walter0807/MotionBERT/train_action_1shot.py
code served (permissive licence) · get_code("66db75824a727d6b")
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 0, dtype family float, shape () 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 torch.nn as nn
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Define a simple model that outputs features
class SimpleFeatureModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=8):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Create tiny datasets
# Anchor (train) loader: 2 samples, input dim 4, output label dim 1
anchor_input = torch.randn(2, 4)
anchor_labels = torch.tensor([0, 1])
anchor_dataset = TensorDataset(anchor_input, anchor_labels)
anchor_loader = DataLoader(anchor_dataset, batch_size=1)

# Test loader: 2 samples, input dim 4, output label dim 1
test_input = torch.randn(2, 4)
test_labels = torch.tensor([1, 0])
test_dataset = TensorDataset(test_input, test_labels)
test_loader = DataLoader(test_dataset, batch_size=1)

# Create model
model = SimpleFeatureModel(input_dim=4, output_dim=8)

ARGS = {
    "anchor_loader": anchor_loader,
    "test_loader": test_loader,
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
solve_scale Not yet run
unverified (harvested, no recorded run)
Walter0807/MotionBERT/infer_wild_mesh.py
code served (permissive licence) · get_code("775e1419f4a8e087")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
Walter0807/MotionBERT/train_action.py
code served (permissive licence) · get_code("ed6e8cfa9cd438dc")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
Walter0807/MotionBERT/train_mesh.py
code served (permissive licence) · get_code("b91c99fd64360d1a")
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, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 5 later) and 6 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
drop_path 224 other papers
56 dated earlier, 3 the same month, 162 later, 2 same year, order not determinable, 1 undated · 38 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
and 221 more not named here
trunc_normal_ 160 other papers
42 dated earlier, 2 the same month, 115 later, 1 same year, order not determinable · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
mpjpe 2 other papers
2 later
2310.16288 (2023-10)
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network
2312.03703 (2023-12)
Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning
loss_mpjpe 1 other paper
1 later
2312.03703 (2023-12)
Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning
p_mpjpe 1 other paper
1 later
2312.03703 (2023-12)
Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning

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

We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations. The motion representations acquired in this way incorporate geometric, kinematic, and physical knowledge about human motion, which can be easily transferred to multiple downstream tasks. We implement the motion encoder with a Dual-stream Spatio-temporal Transformer (DSTformer) neural network. It could capture long-range spatio-temporal relationships among the skeletal joints comprehensively and adaptively, exemplified by the lowest 3D pose estimation error so far when trained from scratch. Furthermore, our proposed framework achieves state-of-the-art performance on all three downstream tasks by simply finetuning the pretrained motion encoder with a simple regression head (1-2 layers), which demonstrates the versatility of the learned motion representations. Code and models are available at https://motionbert.github.io/

For agents

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

get_harvested_code_for_paper("2210.06551")
get_code_for_paper("2210.06551")
have("2210.06551")

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

curl https://syntology.ai/api/ran/2210.06551.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.06551.svg)](https://syntology.ai/paper/2210.06551)

Connect an agent — have() is free.