SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06225 · CVPR · 2024

MoST: Motion Style Transformer between Diverse Action Contents

Jin Choi, Hyung Chang, Jungho Kim, Boeun Kim

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 2 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/2403.06225.json · badge: /api/ran/2403.06225.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
Boeun-Kim/MoST community
Papers with Code archive
7 ran · 2 no recorded run
FunctionStatusWhere it lives
AdaIN Ran
ran on a synthesized input
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("f1b8876565fa84d7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, 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 torch
import torch.nn as nn

# INIT_ARGS: sty_dim and out_dim
INIT_ARGS = {
    'sty_dim': 8,
    'out_dim': 6
}

# ARGS: x and s for forward method
# x should be a 4D tensor (batch, channels, height, width) where channels = out_dim
# s should be a 2D tensor (batch, sty_dim)
ARGS = {
    'x': torch.randn(2, 6, 4, 4),  # batch=2, channels=6 (out_dim), height=4, width=4
    's': torch.randn(2, 8)          # batch=2, sty_dim=8
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Attention Ran
ran on a synthesized input
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("e13e7ac880e2b43b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, 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 torch
import torch.nn as nn

# INIT_ARGS for Attention.__init__
INIT_ARGS = {
    'dim_emb': 12,
    'num_heads': 4,
    'qkv_bias': True,
    'attn_do_rate': 0.1,
    'proj_do_rate': 0.1
}

# ARGS for Attention.forward
# B=2, N=5 (sequence length), C=12 (dim_emb)
x = torch.randn(2, 5, 12)

# Optional mask: shape should be broadcastable with attention scores
# Attention scores will be (B, num_heads, N, N) = (2, 4, 5, 5)
# Mask can be (1, 1, 5, 5) or (2, 4, 5, 5) etc.
mask = torch.ones(1, 1, 5, 5)
mask[:, :, :, 3:] = 0  # Mask out last 2 positions

ARGS = {
    'x': x,
    'mask': mask
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
CrossAttention Ran
ran on a synthesized input · constructed an object; no result was computed
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("1a6a8c5cc76b3eb9")
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 an instance of its own class, CrossAttention: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Define the CrossAttention class
class CrossAttention(nn.Module):

    def __init__(self, dim_emb, num_heads=8, qkv_bias=False, attn_do_rate=0.0, proj_do_rate=0.0):
        super().__init__()
        self.dim_emb = dim_emb
        self.num_heads = num_heads
        dim_each_head = dim_emb // num_heads
        self.scale = dim_each_head ** (-0.5)
        self.q = nn.Linear(dim_emb, dim_emb, bias=qkv_bias)
        self.k = nn.Linear(dim_emb, dim_emb, bias=qkv_bias)
        self.v = nn.Linear(dim_emb, dim_emb, bias=qkv_bias)
        self.attn_dropout = nn.Dropout(attn_do_rate)
        self.proj = nn.Linear(dim_emb, dim_emb)
        self.proj_dropout = nn.Dropout(proj_do_rate)

    def forward(self, x, y, z, mask=None):
        B, N, C = x.shape
        q = self.q(x)
        k = self.k(y)
        v = self.v(z)
        q = q.reshape(B, N, 1, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        k = k.reshape(B, N, 1, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        v = v.reshape(B, N, 1, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        attn = q @ k.transpose(-2, -1) * self.scale
        if mask is not None:
            attn = attn.masked_fill(mask == 0, -1000000000.0)
        attn = attn.softmax(dim=-1)
        attn = self.attn_dropout(attn)
        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_dropout(x)
        return x

# Create tensors for forward pass
batch_size = 2
seq_len = 3
dim_emb = 4
num_heads = 2

x = torch.randn(batch_size, seq_len, dim_emb)
y = torch.randn(batch_size, seq_len, dim_emb)
z = torch.randn(batch_size, seq_len, dim_emb)
mask = torch.ones(batch_size, num_heads, seq_len, seq_len)

# Define ARGS dict with all parameters
ARGS = {
    'dim_emb': dim_emb,
    'num_heads': num_heads,
    'qkv_bias': False,
    'attn_do_rate': 0.1,
    'proj_do_rate': 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CrossAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CrossAttention 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
FeedForward Ran
ran on a synthesized input · constructed an object; no result was computed
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("729f85e02916859e")
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 an instance of its own class, FeedForward: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Create a small input tensor for testing
# Shape: (batch_size=2, in_features=4)
x = torch.randn(2, 4)

# Define ARGS dict with all parameters for FeedForward.__init__
ARGS = {
    'in_features': 4,
    'hidden_features': 8,
    'out_features': 3,
    'do_rate': 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FeedForward — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FeedForward 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
PositionalEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("7478fe455cccc0e9")
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 an instance of its own class, PositionalEmbedding: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

# PositionalEmbedding.__init__ takes:
# - d_model: int (dimensionality of the model)
# - max_len: int (maximum sequence length, default=150)

# PositionalEmbedding.forward takes:
# - x: tensor (used to get x.size(1) for sequence length)

# Create a small input tensor for testing
# Shape: (batch_size=2, seq_len=3, d_model=4)
x = torch.randn(2, 3, 4)

ARGS = {
    'd_model': 4,
    'max_len': 150
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PositionalEmbedding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PositionalEmbedding 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
TransformerDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("82570a9b0ec89da9")
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 an instance of its own class, TransformerDecoder: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math
from einops import rearrange

torch.manual_seed(0)

# Small stand-in classes and tensors
batch_size = 2
num_frames = 8
num_parts = 6
dim_emb = 4
num_heads = 2

# Create valid arguments for TransformerDecoder
cnt_dynamics = torch.randn(batch_size, num_frames, num_parts, dim_emb)
modulated_sty_feat = torch.randn(batch_size, dim_emb * num_parts)

# Create attention mask (optional, but we'll include it)
cnt_mask = torch.ones(batch_size, num_frames, num_frames)

ARGS = {
    'num_part': num_parts,
    'num_frame': num_frames,
    'dim_emb': dim_emb,
    'num_heads': num_heads,
    'ff_expand': 1.0,
    'qkv_bias': False,
    'attn_do_rate': 0.1,
    'proj_do_rate': 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TransformerDecoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerDecoder 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
TransformerEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("0d06bcc45b45732a")
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 an instance of its own class, TransformerEncoder: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "is_cont_enc": False,
    "num_part": 6,
    "num_frame": 4,
    "dim_emb": 8,
    "num_heads": 2,
    "ff_expand": 1.5,
    "qkv_bias": False,
    "attn_do_rate": 0.1,
    "proj_do_rate": 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TransformerEncoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerEncoder 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
StyleTransformer Not yet run
unverified (harvested, no recorded run)
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("42c4c0e4b30058ca")
How it ran

no invocation recorded.

TransformerModulator Not yet run
unverified (harvested, no recorded run)
Boeun-Kim/MoST/model/networks.py
code served (permissive licence) · get_code("9ab9ff74f52e41e6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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, 0 later) and 8 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
PositionalEmbedding
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2207.06101 (2022-07)
Global-local Motion Transformer for Unsupervised Skeleton-based Action 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

While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents. This challenge lies in the lack of clear separation between content and style of a motion. To tackle this challenge, we propose a novel motion style transformer that effectively disentangles style from content and generates a plausible motion with transferred style from a source motion. Our distinctive approach to achieving the goal of disentanglement is twofold: (1) a new architecture for motion style transformer with 'partattentive style modulator across body parts' and 'Siamese encoders that encode style and content features separately'; (2) style disentanglement loss. Our method outperforms existing methods and demonstrates exceptionally high quality, particularly in motion pairs with different contents, without the need for heuristic post-processing. Codes are available at https://github.com/Boeun-Kim/MoST.

For agents

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

get_harvested_code_for_paper("2403.06225")
get_code_for_paper("2403.06225")
have("2403.06225")

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

curl https://syntology.ai/api/ran/2403.06225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.06225.svg)](https://syntology.ai/paper/2403.06225)

Connect an agent — have() is free.