SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1705.02445 · 2017

On human motion prediction using recurrent neural networks

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/1705.02445.json · badge: /api/ran/1705.02445.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
una-dinosauria/human-motion-prediction canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
facebookresearch/QuaterNet reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
define_actions Ran
ran; our contract draft was wrong, not the code
una-dinosauria/human-motion-prediction/src/translate.py
code served (permissive licence) · get_code("a78f69de6209a37d")
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 list, 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 numpy as np

torch.manual_seed(0)

# The function takes a single parameter 'action' which is a string
# It checks if the action is in a predefined list, or if it's "all" or "all_srnn"
# The function expects string inputs

ARGS = {
    "action": "walking"
}
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 list, ndim 1, dtype family float — a list 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
find_indices_srnn Ran
ran, honoured the contract we drafted
facebookresearch/QuaterNet/test_short_term.py
pointer only (licence: NOASSERTION) · get_code("226cc0d55e1dd2d7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/QuaterNet (NOASSERTION). 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.

running_average Ran
ran; our contract draft was wrong, not the code
una-dinosauria/human-motion-prediction/src/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
build_sequence_map_srnn Not yet run
unverified (harvested, no recorded run)
facebookresearch/QuaterNet/test_short_term.py
pointer only (licence: NOASSERTION) · get_code("c272273df06b0856")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/QuaterNet (NOASSERTION). 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. No invocation recorded.

get_test_data Not yet run
unverified (harvested, no recorded run)
facebookresearch/QuaterNet/test_short_term.py
pointer only (licence: NOASSERTION) · get_code("4029d107f867a68d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/QuaterNet (NOASSERTION). 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. No invocation recorded.

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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
running_average 2 other papers
2 later
1805.00655 (2018-05)
Convolutional Sequence to Sequence Model for Human Dynamics
1809.03036 (2018-09)
A Neural Temporal Model for Human Motion Prediction

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following the success of deep learning methods in several computer vision tasks, recent work has focused on using deep recurrent neural networks (RNNs) to model human motion, with the goal of learning time-dependent representations that perform tasks such as short-term motion prediction and long-term human motion synthesis. We examine recent work, with a focus on the evaluation methodologies commonly used in the literature, and show that, surprisingly, state-of-the-art performance can be achieved by a simple baseline that does not attempt to model motion at all. We investigate this result, and analyze recent RNN methods by looking at the architectures, loss functions, and training procedures used in state-of-the-art approaches. We propose three changes to the standard RNN models typically used for human motion, which result in a simple and scalable RNN architecture that obtains state-of-the-art performance on human motion prediction.

For agents

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

get_harvested_code_for_paper("1705.02445")
get_code_for_paper("1705.02445")
have("1705.02445")

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

curl https://syntology.ai/api/ran/1705.02445.json

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

[![Syntology run record](https://syntology.ai/api/ran/1705.02445.svg)](https://syntology.ai/paper/1705.02445)

Connect an agent — have() is free.