SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09703 · 2021

MaCLR: Motion-aware Contrastive Learning of Representations for Videos

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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; 2 failures 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/2106.09703.json · badge: /api/ran/2106.09703.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
amazon-science/self-supervised-maclr canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
construct_optimizer Ran
ran on a synthesized input
amazon-science/self-supervised-maclr/slowfast/models/optimizer.py
code served (permissive licence) · get_code("06282ee2b8b703dc")
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 SGD. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model with batch norm and non-bn parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.bn_layer = nn.BatchNorm1d(4)
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        x = self.bn_layer(x)
        x = self.linear(x)
        return x

model = SimpleModel()

# Create a config object with all required attributes
class Config:
    class MODEL:
        CLS_ONLY = False
    
    class BN:
        WEIGHT_DECAY = 1e-4
    
    class SOLVER:
        OPTIMIZING_METHOD = 'sgd'
        BASE_LR = 0.01
        MOMENTUM = 0.9
        WEIGHT_DECAY = 1e-4
        DAMPENING = 0.0
        NESTEROV = True

cfg = Config()

# Create opt_params by extracting named parameters
opt_params = list(model.named_parameters())

ARGS = {
    'model': model,
    'cfg': cfg,
    'opt_params': opt_params
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
amazon-science/self-supervised-maclr/slowfast/models/common.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("bcc1cdae3bb3212c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from rajatmodi62/OccludedActionBenchmark, and GitHub detected no licence in that repository 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.

get_loss_func Ran
ran; our contract draft was wrong, not the code
amazon-science/self-supervised-maclr/slowfast/models/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("c90b5f606f54d4f7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Wenhao-Chi/UNIEGO, and GitHub could not classify the licence of that repository (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.

wrap_distributed_model Ran
ran on a synthesized input
amazon-science/self-supervised-maclr/slowfast/models/build.py
code served (permissive licence) · get_code("690eba49225ad86f")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

# Create a minimal config class with the required attributes
class Config:
    def __init__(self):
        self.NUM_GPUS = 0  # CPU only
        self.TRAIN = TrainConfig()

class TrainConfig:
    def __init__(self):
        self.MIX_PRECISION_LEVEL = 'O0'

# Create a minimal model
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create config, model, and optimizer
cfg = Config()
model = MinimalModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

ARGS = {
    'cfg': cfg,
    'model': model,
    'optimizer': optimizer,
    'gpu_id': None
}
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
attention_pool Not yet run
unverified (harvested, no recorded run)
amazon-science/self-supervised-maclr/slowfast/models/attention.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("a4723eab8df61dbe")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from rajatmodi62/OccludedActionBenchmark, and GitHub detected no licence in that repository 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. No invocation recorded.

get_trans_func Not yet run
unverified (harvested, no recorded run)
amazon-science/self-supervised-maclr/slowfast/models/resnet_helper.py
code served (permissive licence) · get_code("1c1fa7933939a08f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 later) and 3 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
get_loss_func 13 other papers
2 dated earlier, 11 later
1812.03982 (2018-12)
SlowFast Networks for Video Recognition
2105.11731 (2021-05)
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos
2110.07058 (2021-10)
Ego4D: Around the World in 3,000 Hours of Egocentric Video
and 10 more not named here
drop_path 11 other papers
11 later
2110.06915 (2021-10)
Object-Region Video Transformers
2110.07058 (2021-10)
Ego4D: Around the World in 3,000 Hours of Egocentric Video
136950068 (2022 (year only))
Efficient Video Transformers with Spatial-Temporal Token Selection
and 8 more not named here
attention_pool 8 other papers
8 later
2110.06915 (2021-10)
Object-Region Video Transformers
136950068 (2022 (year only))
Efficient Video Transformers with Spatial-Temporal Token Selection
2203.10233 (2022-03)
DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
and 5 more not named here

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 present MaCLR, a novel method to explicitly perform cross-modal self-supervised video representations learning from visual and motion modalities. Compared to previous video representation learning methods that mostly focus on learning motion cues implicitly from RGB inputs, MaCLR enriches standard contrastive learning objectives for RGB video clips with a cross-modal learning objective between a Motion pathway and a Visual pathway. We show that the representation learned with our MaCLR method focuses more on foreground motion regions and thus generalizes better to downstream tasks. To demonstrate this, we evaluate MaCLR on five datasets for both action recognition and action detection, and demonstrate state-of-the-art self-supervised performance on all datasets. Furthermore, we show that MaCLR representation can be as effective as representations learned with full supervision on UCF101 and HMDB51 action recognition, and even outperform the supervised representation for action recognition on VidSitu and SSv2, and action detection on AVA.

For agents

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

get_harvested_code_for_paper("2106.09703")
get_code_for_paper("2106.09703")
have("2106.09703")

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

curl https://syntology.ai/api/ran/2106.09703.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09703.svg)](https://syntology.ai/paper/2106.09703)

Connect an agent — have() is free.