SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.06803 · 2020

TAM: Temporal Adaptive Module for Video Recognition

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 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 5 have no contract verdict; 0 failures of our instrument; 6 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/2005.06803.json · badge: /api/ran/2005.06803.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
liu-zhy/TANet canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
liu-zhy/temporal-adaptive-module canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_ip Ran
ran on a synthesized input
liu-zhy/TANet/ops/dist_utils.py
code served (permissive licence) · get_code("8aa1bb59c94441a2")
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 re

def get_ip(ip_str):
    """
    input format: SH-IDC1-10-5-30-[137,152] or SH-IDC1-10-5-30-[137-142,152] or SH-IDC1-10-5-30-[152, 137-142]
    output format 10.5.30.137
    """
    return '.'.join(re.findall('\\d+', ip_str)[1:5])

ARGS = {
    "ip_str": "SH-IDC1-10-5-30-[137,152]"
}
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
return_hmdb51 Ran
ran on a synthesized input
liu-zhy/TANet/ops/dataset_config.py
code served (permissive licence) · get_code("da3f1f7cf67362e2")
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 numpy as np

torch.manual_seed(0)

ARGS = {
    'modality': 'RGB'
}
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 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_something Ran
ran on a synthesized input
liu-zhy/TANet/ops/dataset_config.py
code served (permissive licence) · get_code("48f65a4712d42061")
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 = {
    'modality': 'RGB'
}
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_ucf101 Ran
ran on a synthesized input
liu-zhy/TANet/ops/dataset_config.py
code served (permissive licence) · get_code("2aa6d9e3ae6cf167")
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 numpy as np

torch.manual_seed(0)

# The function return_ucf101 takes a single parameter 'modality'
# and returns a tuple of values based on that modality.
# Valid modalities are 'RGB' and 'Flow'

ARGS = {
    'modality': 'RGB'
}
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 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
softmax Ran
ran on a synthesized input
liu-zhy/TANet/ops/utils.py
code served (permissive licence) · get_code("2fc0c71db48a9af8")
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 2, dtype family float, shape (2, 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 small scores array for the softmax function
# Shape: (2, 4) - batch size 2, 4 classes
scores = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 1.0, 4.0, 3.0]
], dtype=np.float32)

ARGS = {
    'scores': scores
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
accuracy Not yet run
unverified (harvested, no recorded run)
liu-zhy/TANet/ops/utils.py
code served (permissive licence) · get_code("f0c9a29156911331")
How it ran

no invocation recorded.

accuracy Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from swathikirans/GSM
pointer only; the stored copy get_code serves, from swathikirans/GSM, is pointer only (licence: NOASSERTION) · get_code("b02c6e331bc88d68")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

bninception Not yet run
unverified (harvested, no recorded run)
liu-zhy/TANet/archs/bn_inception.py
code served (permissive licence) · get_code("c89c29bd79c97227")
How it ran

no invocation recorded.

eval_video Not yet run
unverified (harvested, no recorded run)
liu-zhy/temporal-adaptive-module/test_models.py
code served (permissive licence) · get_code("25a2a9af3ae42ab2")
How it ran

no invocation recorded.

make_temporal_modeling Not yet run
unverified (harvested, no recorded run)
liu-zhy/TANet/ops/temporal_module.py
code served (permissive licence) · get_code("3463156e190cae52")
How it ran

no invocation recorded.

parse_shift_option_from_log_name Not yet run
unverified (harvested, no recorded run)
liu-zhy/temporal-adaptive-module/test_models.py
code served (permissive licence) · get_code("cb4f97c8c0af5da8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 10 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, 3 later) and 7 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
accuracy 71 other papers
28 dated earlier, 43 later · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
and 68 more not named here
bninception 2 other papers
1 dated earlier, 1 later
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
2203.13611 (2022-03)
Class-Incremental Learning for Action Recognition in Videos
softmax 2 other papers
1 dated earlier, 1 later
2001.06499 (2020-01)
Temporal Interlacing Network
2007.09933 (2020-07)
MotionSqueeze: Neural Motion Feature Learning for Video Understanding

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

Video data is with complex temporal dynamics due to various factors such as camera motion, speed variation, and different activities. To effectively capture this diverse motion pattern, this paper presents a new temporal adaptive module ({\bf TAM}) to generate video-specific temporal kernels based on its own feature map. TAM proposes a unique two-level adaptive modeling scheme by decoupling the dynamic kernel into a location sensitive importance map and a location invariant aggregation weight. The importance map is learned in a local temporal window to capture short-term information, while the aggregation weight is generated from a global view with a focus on long-term structure. TAM is a modular block and could be integrated into 2D CNNs to yield a powerful video architecture (TANet) with a very small extra computational cost. The extensive experiments on Kinetics-400 and Something-Something datasets demonstrate that our TAM outperforms other temporal modeling methods consistently, and achieves the state-of-the-art performance under the similar complexity. The code is available at \url{ https://github.com/liu-zhy/temporal-adaptive-module}.

For agents

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

get_harvested_code_for_paper("2005.06803")
get_code_for_paper("2005.06803")
have("2005.06803")

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

curl https://syntology.ai/api/ran/2005.06803.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.06803.svg)](https://syntology.ai/paper/2005.06803)

Connect an agent — have() is free.