SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.13426 · 2020

Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics

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; 3 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures 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/2008.13426.json · badge: /api/ran/2008.13426.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
laura-wang/video_repres_sts canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
laura-wang/video_repres_mas canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
cell_gradient Ran
ran, honoured the contract we drafted
laura-wang/video_repres_sts/sts/compute_motion_statistics_fast.py
pointer only (licence: NONE) · get_code("ccf44b771f7e8ab9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, laura-wang/video_repres_sts 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.

compute_motion_pattern_1 Ran
ran, honoured the contract we drafted
laura-wang/video_repres_sts/sts/compute_motion_statistics_fast.py
pointer only (licence: NONE) · get_code("68fda699840fc37b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, laura-wang/video_repres_sts 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.

compute_motion_pattern_2 Ran
ran, honoured the contract we drafted
laura-wang/video_repres_sts/sts/compute_motion_statistics_fast.py
pointer only (licence: NONE) · get_code("68394755cc7801db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, laura-wang/video_repres_sts 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.

pattern_1 Ran
ran on a synthesized input
laura-wang/video_repres_mas/comput_motion_statistics_fast.py
code served (permissive licence) · get_code("7b838307bdea4c62")
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

# The function pattern_1 takes two parameters:
# - mag: a 2D numpy array of shape (112, 112) - it's indexed with [x_start:x_end, y_start:y_end]
#        where x ranges from 0 to 112 and y ranges from 0 to 112 (4 blocks of 28 each)
# - ang: a 2D numpy array of the same shape - gradient angles

# Create magnitude array (112x112)
mag = np.random.rand(112, 112) * 100

# Create angle array (112x112) with values in range [0, 360)
ang = np.random.rand(112, 112) * 360

ARGS = {
    "mag": mag,
    "ang": ang
}
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
pattern_2 Ran
ran on a synthesized input
laura-wang/video_repres_mas/comput_motion_statistics_fast.py
code served (permissive licence) · get_code("de8e1dcb0336aaff")
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

# The function pattern_2 expects:
# - mag: a 2D numpy array of shape (112, 112) with magnitude values
# - ang: a 2D numpy array of shape (112, 112) with angle values (in degrees)

# Create sample magnitude array (112x112)
mag = np.random.rand(112, 112) * 100

# Create sample angle array (112x112) with values in range [0, 360)
ang = np.random.rand(112, 112) * 360

ARGS = {
    "mag": mag,
    "ang": ang
}
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

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, 0 are also present in other papers whose code we hold (0 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.

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

This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc. Then a neural network is built and trained to yield the statistical summaries given the video frames as inputs. In order to alleviate the learning difficulty, we employ several spatial partitioning patterns to encode rough spatial locations instead of exact spatial Cartesian coordinates. Our approach is inspired by the observation that human visual system is sensitive to rapidly changing contents in the visual field, and only needs impressions about rough spatial locations to understand the visual contents. To validate the effectiveness of the proposed approach, we conduct extensive experiments with four 3D backbone networks, i.e., C3D, 3D-ResNet, R(2+1)D and S3D-G. The results show that our approach outperforms the existing approaches across these backbone networks on four downstream video analysis tasks including action recognition, video retrieval, dynamic scene recognition, and action similarity labeling. The source code is publicly available at: https://github.com/laura-wang/video_repres_sts.

For agents

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

get_harvested_code_for_paper("2008.13426")
get_code_for_paper("2008.13426")
have("2008.13426")

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

curl https://syntology.ai/api/ran/2008.13426.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.13426.svg)](https://syntology.ai/paper/2008.13426)

Connect an agent — have() is free.