SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.07205 · ICCV · 2023

Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

Fabio Galasso, Alessandro Flaborea, Bardh Prenkaj, Luca Collorone, Guido Maria D'amely, Di Melendugno, Stefano D'arrigo

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 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/2307.07205.json · badge: /api/ran/2307.07205.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
aleflabo/MoCoDAD canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
adjust_lr Ran
ran; our contract draft was wrong, not the code
aleflabo/MoCoDAD/utils/model_utils.py
code served (permissive licence) · get_code("935b328e2a4ca4dd")
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 1, 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
from torch.optim import SGD
from torch.optim.lr_scheduler import StepLR

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Create a scheduler
scheduler = StepLR(optimizer, step_size=1, gamma=0.9)

# Test case 1: Using scheduler
ARGS = {
    'optimizer': optimizer,
    'epoch': 5,
    'lr': None,
    'lr_decay': None,
    'scheduler': scheduler
}
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 tuple, ndim 1, 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
calc_reg_loss Ran
ran, honoured the contract we drafted
aleflabo/MoCoDAD/utils/model_utils.py
code served (permissive licence) · get_code("e8961ce4b45db673")
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. 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

torch.manual_seed(0)

# Create a small model with named parameters (including bias and non-bias)
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# The function accesses model.named_parameters() and model.device
# Verify the model has the expected structure
_ = list(model.named_parameters())

ARGS = {
    'model': model,
    'reg_type': 'l2',
    'avg': True
}
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 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
compute_bounding_box Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aleflabo/MoCoDAD/utils/data.py
code served (permissive licence) · get_code("1aaf243c5f555511")
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 1, dtype family int; 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

# Create keypoints array with shape (num_keypoints * 2,)
# Using 5 keypoints, so 10 values total (5 * 2)
keypoints = np.array([100.5, 150.2, 200.0, 180.5, 250.3, 160.0, 0.0, 0.0, 120.0, 140.0], dtype=np.float32)

# Create video resolution array with shape (2,) and dtype float32
video_resolution = np.array([640.0, 480.0], dtype=np.float32)

ARGS = {
    "keypoints": keypoints,
    "video_resolution": video_resolution,
    "return_discrete_values": True
}
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 tuple, ndim 1, dtype family int — 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
create_experiment_dirs Ran
ran; our contract draft was wrong, not the code
aleflabo/MoCoDAD/utils/argparser.py
code served (permissive licence) · get_code("d7470d4a55a861f0")
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 str. 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 os
import tempfile

class Args:
    def __init__(self):
        self.dataset_choice = "cifar10"
        self.exp_dir = tempfile.gettempdir()
        self.dir_name = "experiment_001"
        self.create_experiment_dir = True

ARGS = {
    "args": Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
extract_global_features Ran
ran; our contract draft was wrong, not the code
aleflabo/MoCoDAD/utils/data.py
code served (permissive licence) · get_code("07a93aced16ac5c7")
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 dict. 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)

class MockTrajectory:
    def __init__(self):
        self.data = torch.randn(2, 4)
    
    def use_global_features(self, video_resolution, extract_delta=False, use_first_step_as_reference=False):
        # Mock implementation that accepts the parameters
        self.video_resolution = video_resolution
        self.extract_delta = extract_delta
        self.use_first_step_as_reference = use_first_step_as_reference

trajectories = {
    'traj_0': MockTrajectory(),
    'traj_1': MockTrajectory(),
}

ARGS = {
    'trajectories': trajectories,
    'video_resolution': (1080, 1920),
    'extract_delta': False,
    'use_first_step_as_reference': False,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
init_args Ran
ran; our contract draft was wrong, not the code
aleflabo/MoCoDAD/utils/argparser.py
code served (permissive licence) · get_code("2e4def30e7a3be32")
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 Args. 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 os
import tempfile

class Args:
    def __init__(self):
        self.dataset_choice = 'STC'
        self.exp_dir = tempfile.gettempdir()
        self.dir_name = 'test_experiment'
        self.create_experiment_dir = True
        self.debug = False
        self.ae_epochs = 50
        self.test_path = '/tmp/test_gt'
        self.data_dir = tempfile.gettempdir()
        self.validation = True
        self.ckpt_dir = None

args_obj = Args()

ARGS = {
    'args': args_obj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Args — a Args output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Args 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
get_optim_and_scheduler Not yet run
unverified (harvested, no recorded run)
aleflabo/MoCoDAD/utils/model_utils.py
code served (permissive licence) · get_code("7e0144cbf00fd665")
How it ran

no invocation recorded.

load_trajectories Not yet run
unverified (harvested, no recorded run)
aleflabo/MoCoDAD/utils/data.py
code served (permissive licence) · get_code("f7e3b54a8686d2b2")
How it ran

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
adjust_lr 1 other paper
1 dated earlier
2301.09489 (2023-01)
Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection
calc_reg_loss 1 other paper
1 dated earlier
2301.09489 (2023-01)
Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection
get_optim_and_scheduler 1 other paper
1 dated earlier
2301.09489 (2023-01)
Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection

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

Anomalies are rare and anomaly detection is often therefore framed as One-Class Classification (OCC), i.e. trained solely on normalcy. Leading OCC techniques constrain the latent representations of normal 1 motions to limited volumes and detect as abnormal anything outside, which accounts satisfactorily for the openset'ness of anomalies. But normalcy shares the same openset'ness property since humans can perform the same action in several ways, which the leading techniques neglect. We propose a novel generative model for video anomaly detection (VAD), which assumes that both normality and abnormality are multimodal. We consider skeletal representations and leverage state-of-the-art diffusion probabilistic models to generate multimodal future human poses. We contribute a novel conditioning on the past motion of people and exploit the improved mode coverage capabilities of diffusion processes to generate different-but-plausible future motions. Upon the statistical aggregation of future modes, an anomaly is detected when the generated set of motions is not pertinent to the actual future. We validate our model on 4 established benchmarks: UBnormal, HR-UBnormal, HR-STC, and HR-Avenue, with extensive experiments surpassing state-of-the-art results.

For agents

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

get_harvested_code_for_paper("2307.07205")
get_code_for_paper("2307.07205")
have("2307.07205")

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

curl https://syntology.ai/api/ran/2307.07205.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.07205.svg)](https://syntology.ai/paper/2307.07205)

Connect an agent — have() is free.