SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.03036 · 2018

A Neural Temporal Model for Human Motion Prediction

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 0 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/1809.03036.json · badge: /api/ran/1809.03036.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
cr7anand/neural_temporal_models canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
last_buffer_frame Ran
ran on a synthesized input
cr7anand/neural_temporal_models/baselines.py
code served (permissive licence) · get_code("fc6b1b1e88c10b87")
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 numpy as np

# Construct valid arguments for last_buffer_frame function

# The function expects:
# - actions_dict: Dictionary mapping action names to tuples of (enc_in, dec_in, dec_out)
#   where each of enc_in, dec_in, dec_out is a list of arrays
# - actions: List of action name strings

# enc_in: encoder input - list of arrays with shape (seq_len_in, feature_dim)
# dec_in: decoder input - list of arrays with shape (seq_len_in, feature_dim)
# dec_out: decoder output - list of arrays with shape (seq_len_out, feature_dim)

n_sequences = 2
seq_len_in = 5
seq_len_out = 10
feature_dim = 8

# Create encoder input data (list of arrays)
enc_in_action1 = [np.random.randn(seq_len_in, feature_dim) for _ in range(n_sequences)]
dec_in_action1 = [np.random.randn(seq_len_in, feature_dim) for _ in range(n_sequences)]
dec_out_action1 = [np.random.randn(seq_len_out, feature_dim) for _ in range(n_sequences)]

# Create encoder input data for second action
enc_in_action2 = [np.random.randn(seq_len_in, feature_dim) for _ in range(n_sequences)]
dec_in_action2 = [np.random.randn(seq_len_in, feature_dim) for _ in range(n_sequences)]
dec_out_action2 = [np.random.randn(seq_len_out, feature_dim) for _ in range(n_sequences)]

# Construct actions_dict
actions_dict = {
    'walking': (enc_in_action1, dec_in_action1, dec_out_action1),
    'running': (enc_in_action2, dec_in_action2, dec_out_action2)
}

# List of action keys
actions = ['walking', 'running']

ARGS = {
    'actions_dict': actions_dict,
    'actions': actions
}
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 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
quat2expmap Ran
ran on a synthesized input
cr7anand/neural_temporal_models/data_utils.py
code served (permissive licence) · get_code("b75bbc404507d0ee")
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 float, 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

# Construct a valid quaternion (normalized)
# A quaternion has the form [w, x, y, z] where w is the scalar part
# and [x, y, z] is the vector part
# For a valid quaternion, the L2 norm must be 1

q = np.array([0.7071, 0.7071, 0.0, 0.0], dtype=np.float32)

# Verify it's normalized
q = q / np.linalg.norm(q)

ARGS = {
    "q": q
}
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 float, 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
rotmat2euler Ran
ran, honoured the contract we drafted
cr7anand/neural_temporal_models/data_utils.py
code served (permissive licence) · get_code("933d9a6e6db37858")
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 float, 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

# Construct a valid 3x3 rotation matrix
# Using a simple rotation matrix around the z-axis
angle = np.pi / 4
R = np.array([
    [np.cos(angle), -np.sin(angle), 0],
    [np.sin(angle), np.cos(angle), 0],
    [0, 0, 1]
])

ARGS = {
    "R": R
}
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 float, 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
rotmat2quat Ran
ran, honoured the contract we drafted
cr7anand/neural_temporal_models/data_utils.py
code served (permissive licence) · get_code("79f4ca59c2ff064b")
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 float, shape (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 numpy as np

# Create a valid 3x3 rotation matrix
# Using a simple rotation matrix for 45 degrees around z-axis
angle = np.pi / 4
c = np.cos(angle)
s = np.sin(angle)
R = np.array([
    [c, -s, 0],
    [s, c, 0],
    [0, 0, 1]
], dtype=np.float32)

ARGS = {
    "R": R
}
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 float, shape (4,) — shape (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
running_average Ran
ran; our contract draft was wrong, not the code
cr7anand/neural_temporal_models/baselines.py
code served (permissive licence) · get_code("25b6e39c87dde97a")
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 numpy as np

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

# Create small test data
# enc_in: encoder input, shape (n_sequences, seq_length_in, feature_dim)
# dec_in: decoder input, shape (n_sequences, seq_length_in, feature_dim)
# dec_out: decoder output, shape (n_sequences, seq_length_out, feature_dim)

seq_length_in = 5
seq_length_out = 7
feature_dim = 12
n_sequences = 2

# Create encoder input: (n_sequences, seq_length_in, feature_dim)
enc_in_walk = np.random.randn(n_sequences, seq_length_in, feature_dim)
dec_in_walk = np.random.randn(n_sequences, seq_length_in, feature_dim)
dec_out_walk = np.random.randn(n_sequences, seq_length_out, feature_dim)

# Create another action with same structure
enc_in_run = np.random.randn(n_sequences, seq_length_in, feature_dim)
dec_in_run = np.random.randn(n_sequences, seq_length_in, feature_dim)
dec_out_run = np.random.randn(n_sequences, seq_length_out, feature_dim)

# Build the actions_dict
actions_dict = {
    'walk': (
        [enc_in_walk[0], enc_in_walk[1]],  # enc_in as list of arrays
        [dec_in_walk[0], dec_in_walk[1]],  # dec_in as list of arrays
        [dec_out_walk[0], dec_out_walk[1]]  # dec_out as list of arrays
    ),
    'run': (
        [enc_in_run[0], enc_in_run[1]],
        [dec_in_run[0], dec_in_run[1]],
        [dec_out_run[0], dec_out_run[1]]
    )
}

# List of action keys
actions = ['walk', 'run']

# Number of frames for running average
k = 3

ARGS = {
    'actions_dict': actions_dict,
    'actions': actions,
    'k': k
}
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 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

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
rotmat2euler 4 other papers
1 dated earlier, 3 later
1805.00655 (2018-05)
Convolutional Sequence to Sequence Model for Human Dynamics
1908.05436 (2019-08)
Learning Trajectory Dependencies for Human Motion Prediction
136820244 (2022 (year only))
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
and 1 more not named here
rotmat2quat 4 other papers
1 dated earlier, 3 later
1805.00655 (2018-05)
Convolutional Sequence to Sequence Model for Human Dynamics
1908.05436 (2019-08)
Learning Trajectory Dependencies for Human Motion Prediction
136820244 (2022 (year only))
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
and 1 more not named here
running_average 2 other papers
2 dated earlier
1705.02445 (2017-05)
On human motion prediction using recurrent neural networks
1805.00655 (2018-05)
Convolutional Sequence to Sequence Model for Human Dynamics

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 propose novel neural temporal models for predicting and synthesizing human motion, achieving state-of-the-art in modeling long-term motion trajectories while being competitive with prior work in short-term prediction and requiring significantly less computation. Key aspects of our proposed system include: 1) a novel, two-level processing architecture that aids in generating planned trajectories, 2) a simple set of easily computable features that integrate derivative information, and 3) a novel multi-objective loss function that helps the model to slowly progress from simple next-step prediction to the harder task of multi-step, closed-loop prediction. Our results demonstrate that these innovations improve the modeling of long-term motion trajectories. Finally, we propose a novel metric, called Normalized Power Spectrum Similarity (NPSS), to evaluate the long-term predictive ability of motion synthesis models, complementing the popular mean-squared error (MSE) measure of Euler joint angles over time. We conduct a user study to determine if the proposed NPSS correlates with human evaluation of long-term motion more strongly than MSE and find that it indeed does. We release code and additional results (visualizations) for this paper at: https://github.com/cr7anand/neural_temporal_models

For agents

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

get_harvested_code_for_paper("1809.03036")
get_code_for_paper("1809.03036")
have("1809.03036")

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

curl https://syntology.ai/api/ran/1809.03036.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.03036.svg)](https://syntology.ai/paper/1809.03036)

Connect an agent — have() is free.