SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.09805 · 2020

Active Contrastive Learning of Audio-Visual Video Representations

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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 8 have no contract verdict; 0 failures of our instrument; 1 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/2009.09805.json · badge: /api/ran/2009.09805.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
yunyikristy/CM-ACC canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran on a synthesized input
yunyikristy/CM-ACC/resnet1d.py
code served (permissive licence) · get_code("3c68e0b906dbc9ef")
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 Conv2d. 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)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "kernel_size": 3,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
distance Ran
ran on a synthesized input
yunyikristy/CM-ACC/kmeanspp.py
code served (permissive licence) · get_code("b1b989baab3936b2")
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 float64, ndim 0, 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 numpy as np

# The function takes two arguments: x1 and x2
# It computes Euclidean distance between them
# Both should be array-like (numpy arrays work well)
# They need to be the same shape for subtraction

x1 = np.array([1.0, 2.0, 3.0, 4.0])
x2 = np.array([5.0, 6.0, 7.0, 8.0])

ARGS = {
    "x1": x1,
    "x2": x2
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
get_centroids Ran
ran on a synthesized input
yunyikristy/CM-ACC/kmeanspp.py
code served (permissive licence) · get_code("671f375fc050046b")
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, 3) 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 dataset with shape (m, n) where m=5 samples, n=3 features
np.random.seed(0)
dataset = np.random.randn(5, 3)

# Set k to 2 (number of clusters)
k = 2

ARGS = {
    "dataset": dataset,
    "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 ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
get_fine_tuning_parameters Ran
ran on a synthesized input
yunyikristy/CM-ACC/models/densenet.py
code served (permissive licence) · get_code("b934dfd4a7bd8467")
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 torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that mimics DenseNet structure
class MiniDenseNet(nn.Module):
    def __init__(self):
        super().__init__()
        # Create denseblock and transition modules
        self.denseblock1 = nn.Linear(4, 4)
        self.transition1 = nn.Linear(4, 4)
        self.denseblock2 = nn.Linear(4, 4)
        self.transition2 = nn.Linear(4, 4)
        self.denseblock3 = nn.Linear(4, 4)
        self.transition3 = nn.Linear(4, 4)
        self.denseblock4 = nn.Linear(4, 4)
        self.transition4 = nn.Linear(4, 4)
        self.norm5 = nn.BatchNorm1d(4)
        self.classifier = nn.Linear(4, 10)

model = MiniDenseNet()

ARGS = {
    'model': model,
    'ft_begin_index': 2
}
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 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
get_mean Ran
ran on a synthesized input
yunyikristy/CM-ACC/mean.py
code served (permissive licence) · get_code("e83fbcc5be03a1f6")
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)

ARGS = {
    'norm_value': 255,
    'dataset': 'activitynet'
}
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
get_std Ran
ran on a synthesized input
yunyikristy/CM-ACC/mean.py
code served (permissive licence) · get_code("9533d248536bab4a")
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)

ARGS = {
    "norm_value": 255
}
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
nearest Ran
ran on a synthesized input
yunyikristy/CM-ACC/kmeanspp.py
code served (permissive licence) · get_code("f4f584599385bac3")
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 float64, ndim 0, 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 numpy as np

# Create a small point to find nearest cluster center for
point = np.array([1.0, 2.0, 3.0, 4.0])

# Create a small set of cluster centers (3 centers, 4 dimensions each)
cluster_centers = np.array([
    [0.0, 0.0, 0.0, 0.0],
    [1.5, 2.5, 3.5, 4.5],
    [5.0, 5.0, 5.0, 5.0]
])

ARGS = {
    "point": point,
    "cluster_centers": cluster_centers
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
pil_loader Ran
ran, honoured the contract we drafted
yunyikristy/CM-ACC/datasets/activitynet.py
pointer only (licence: MIT); the stored copy get_code serves, from YuemingJin/MTRCNet-CL, is pointer only (licence: NONE) · get_code("1df9a5ffd9b38c34")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from YuemingJin/MTRCNet-CL, 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.

video_loader Ran
ran on a synthesized input
yunyikristy/CM-ACC/datasets/activitynet.py
code served (permissive licence) · get_code("969914385b6159ef")
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 4, 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 os
import tempfile
from PIL import Image
import numpy as np

# Create a temporary directory with test images
temp_dir = tempfile.mkdtemp()

# Create a few test images
for i in range(0, 3):
    img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
    img = Image.fromarray(img_array.transpose(1, 2, 0), 'RGB')
    img_path = os.path.join(temp_dir, f'image_{i:05d}.jpg')
    img.save(img_path)

# Define a simple image loader function
def simple_image_loader(image_path):
    img = Image.open(image_path)
    return np.array(img)

# Define arguments
ARGS = {
    'video_dir_path': temp_dir,
    'frame_indices': [0, 1, 2],
    'image_loader': simple_image_loader
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 4, dtype family int — 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
accimage_loader Not yet run
unverified (harvested, no recorded run)
yunyikristy/CM-ACC/datasets/activitynet.py
code served (permissive licence) · get_code("aae0a4f3535e8f26")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 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
pil_loader 28 other papers
12 dated earlier, 16 later
1702.00758 (2017-02)
HashNet: Deep Learning to Hash by Continuation
1805.07932 (2018-05)
Bilinear Attention Networks
1807.06587 (2018-07)
Deep Exemplar-based Colorization
and 25 more not named here
accimage_loader 3 other papers
1 dated earlier, 2 later
1912.05534 (2019-12)
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
2111.13675 (2021-11)
Weakly-guided Self-supervised Pretraining for Temporal Activity Detection
aaai_25362 (2023 (year only))
Global-Local Characteristic Excited Cross-Modal Attacks from Images to Videos
video_loader 2 other papers
1 dated earlier, 1 later
1912.05534 (2019-12)
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
aaai_25362 (2023 (year only))
Global-Local Characteristic Excited Cross-Modal Attacks from Images to Videos
get_fine_tuning_parameters 1 other paper
1 dated earlier
1912.05534 (2019-12)
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
get_mean 1 other paper
1 dated earlier
2006.15731 (2020-06)
Unsupervised Learning of Video Representations via Dense Trajectory Clustering
get_std 1 other paper
1 dated earlier
2006.15731 (2020-06)
Unsupervised Learning of Video Representations via Dense Trajectory Clustering

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

Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower bound requires a sample size exponential in MI and thus a large set of negative samples. We can incorporate more samples by building a large queue-based dictionary, but there are theoretical limits to performance improvements even with a large number of negative samples. We hypothesize that \textit{random negative sampling} leads to a highly redundant dictionary that results in suboptimal representations for downstream tasks. In this paper, we propose an active contrastive learning approach that builds an \textit{actively sampled} dictionary with diverse and informative items, which improves the quality of negative samples and improves performances on tasks where there is high mutual information in the data, e.g., video classification. Our model achieves state-of-the-art performance on challenging audio and visual downstream benchmarks including UCF101, HMDB51 and ESC50.\footnote{Code is available at: \url{https://github.com/yunyikristy/CM-ACC}}

For agents

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

get_harvested_code_for_paper("2009.09805")
get_code_for_paper("2009.09805")
have("2009.09805")

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

curl https://syntology.ai/api/ran/2009.09805.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.09805.svg)](https://syntology.ai/paper/2009.09805)

Connect an agent — have() is free.