SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.13130 · 2019

Grouped Spatial-Temporal Aggregation for Efficient Action Recognition

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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure 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/1909.13130.json · badge: /api/ran/1909.13130.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
chenxuluo/GST-video community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
return_dataset Ran
ran; our contract draft was wrong, not the code
chenxuluo/GST-video/datasets_video.py
code served (permissive licence) · get_code("9d78c6cc09711d49")
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. 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

# Create a temporary directory structure to simulate the dataset
temp_dir = tempfile.mkdtemp()
ROOT_DATASET = temp_dir + '/'

# Create the necessary directory structure
os.makedirs(os.path.join(temp_dir, 'somethingv1'), exist_ok=True)
os.makedirs(os.path.join(temp_dir, 'somethingv2'), exist_ok=True)

# Create category.txt files
with open(os.path.join(temp_dir, 'somethingv1', 'category.txt'), 'w') as f:
    f.write('action1\n')
    f.write('action2\n')
    f.write('action3\n')

with open(os.path.join(temp_dir, 'somethingv2', 'category.txt'), 'w') as f:
    f.write('action1\n')
    f.write('action2\n')

# Create train.txt files
with open(os.path.join(temp_dir, 'somethingv1', 'train.txt'), 'w') as f:
    f.write('video1 1\n')
    f.write('video2 2\n')

with open(os.path.join(temp_dir, 'somethingv2', 'train.txt'), 'w') as f:
    f.write('video1 1\n')

# Create valid.txt files
with open(os.path.join(temp_dir, 'somethingv1', 'valid.txt'), 'w') as f:
    f.write('video3 1\n')

with open(os.path.join(temp_dir, 'somethingv2', 'valid.txt'), 'w') as f:
    f.write('video2 2\n')

ARGS = {
    'dataset': 'somethingv2',
    'ROOT_DATASET': ROOT_DATASET
}
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 tuple — a tuple output has no array shape of its own; none is 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
return_somethingv1 Ran
ran on a synthesized input
chenxuluo/GST-video/datasets_video.py
code served (permissive licence) · get_code("ef7d80ceb291c003")
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

torch.manual_seed(0)

ARGS = {
    'ROOT_DATASET': '/tmp/datasets/'
}
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
return_somethingv2 Ran
ran on a synthesized input
chenxuluo/GST-video/datasets_video.py
code served (permissive licence) · get_code("d9d848105c68dc31")
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 tempfile
import os

torch.manual_seed(0)

# Create a temporary directory structure to simulate ROOT_DATASET
temp_root = tempfile.mkdtemp()

# Create the somethingv2 subdirectory structure
somethingv2_dir = os.path.join(temp_root, 'somethingv2')
os.makedirs(somethingv2_dir, exist_ok=True)

frames_dir = os.path.join(somethingv2_dir, '20bn-something-something-v2-frames')
os.makedirs(frames_dir, exist_ok=True)

# Create dummy category.txt file
category_file = os.path.join(somethingv2_dir, 'category.txt')
with open(category_file, 'w') as f:
    f.write('category1\ncategory2\n')

# Create dummy train.txt file
train_file = os.path.join(somethingv2_dir, 'train.txt')
with open(train_file, 'w') as f:
    f.write('video1 1\nvideo2 2\n')

# Create dummy valid.txt file
valid_file = os.path.join(somethingv2_dir, 'valid.txt')
with open(valid_file, 'w') as f:
    f.write('video3 1\nvideo4 2\n')

ROOT_DATASET = temp_root + '/'

ARGS = {
    'ROOT_DATASET': ROOT_DATASET
}
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
resnet101 Not yet run
unverified (harvested, no recorded run)
chenxuluo/GST-video/GST.py
code served (permissive licence) · get_code("cf910ac82480d5a5")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
chenxuluo/GST-video/GST.py
code served (permissive licence) · get_code("b4ca2701239e633c")
How it ran

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
return_dataset 1 other paper
1 later
aaai_16433 (2021 (year only))
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks

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

Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to reduce the complexity by decoupling the spatial and temporal filters. In this paper, we propose a novel decomposition method that decomposes the feature channels into spatial and temporal groups in parallel. This decomposition can make two groups focus on static and dynamic cues separately. We call this grouped spatial-temporal aggregation (GST). This decomposition is more parameter-efficient and enables us to quantitatively analyze the contributions of spatial and temporal features in different layers. We verify our model on several action recognition tasks that require temporal reasoning and show its effectiveness.

For agents

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

get_harvested_code_for_paper("1909.13130")
get_code_for_paper("1909.13130")
have("1909.13130")

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

curl https://syntology.ai/api/ran/1909.13130.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.13130.svg)](https://syntology.ai/paper/1909.13130)

Connect an agent — have() is free.