SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.09634 · 2022

A Closer Look at Weakly-Supervised Audio-Visual Source Localization

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 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/2209.09634.json · badge: /api/ran/2209.09634.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
stonemo/slavc canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
concat_all_gather Ran
ran, honoured the contract we drafted
stonemo/slavc/model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from HimangiM/RepLAI, is pointer only (licence: NONE) · get_code("f723ada1d6eea3ab")
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 HimangiM/RepLAI, 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.

load_all_bboxes Ran
ran on a synthesized input
stonemo/slavc/datasets.py
code served (permissive licence) · get_code("9960e524f4ae8a21")
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 dict. 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
import xml.etree.ElementTree as ET

# Create a temporary directory with sample annotation files
temp_dir = tempfile.mkdtemp()

# Create a sample Flickr-style XML annotation file
xml_content = """<?xml version="1.0"?>
<annotation>
    <object>
        <bbox>
            <xmin>64</xmin>
            <ymin>64</ymin>
            <xmax>192</xmax>
            <ymax>192</ymax>
        </bbox>
    </object>
</annotation>
"""

xml_file_path = os.path.join(temp_dir, 'sample_image.xml')
with open(xml_file_path, 'w') as f:
    f.write(xml_content)

ARGS = {
    'annotation_dir': temp_dir,
    'format': 'flickr'
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_image Ran
ran, honoured the contract we drafted
stonemo/slavc/datasets.py
code served (permissive licence) · get_code("989269e62e59af83")
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 Image. 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 tempfile
from PIL import Image

# Create a temporary RGB image file
with tempfile.NamedTemporaryFile(suffix='.png', delete=False) as tmp:
    img = Image.new('RGB', (100, 100), color='red')
    img.save(tmp.name)
    temp_image_path = tmp.name

ARGS = {
    'path': temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
normalize_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
stonemo/slavc/utils.py
code served (permissive licence) · get_code("e7357eb51f7bea31")
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 Tensor, 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 torch

torch.manual_seed(0)

# Create a small tensor for normalization
value = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                      [5.0, 6.0, 7.0, 8.0]])

# Set up ARGS with all parameters
ARGS = {
    'value': value,
    'vmax': None,
    'vmin': 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 Tensor, 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
visualize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
stonemo/slavc/utils.py
code served (permissive licence) · get_code("548ea444cb942399")
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 3, dtype family int, shape (4, 3, 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
import cv2

# Create a small test image (4x3 RGB image in uint8 format)
raw_image = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

# Create a list of bounding boxes in format [xmin, ymin, xmax, ymax]
boxes = [
    [0.5, 0.5, 2.0, 2.5],
    [1.0, 1.0, 3.0, 3.5]
]

ARGS = {
    "raw_image": raw_image,
    "boxes": boxes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 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
build_optimizer_and_scheduler_adam_v2 Not yet run
unverified (harvested, no recorded run)
stonemo/slavc/utils.py
code served (permissive licence) · get_code("e3ffe91745bebb04")
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, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 4 later) and 1 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
load_image 2 other papers
1 dated earlier, 1 later
2004.10016 (2020-04)
Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition
2309.05281 (2023-09)
Class-Incremental Grouping Network for Continual Audio-Visual Learning
normalize_img 2 other papers
1 dated earlier, 1 later
2008.04237 (2020-08)
Self-Supervised Learning of Audio-Visual Objects from Video
2309.05281 (2023-09)
Class-Incremental Grouping Network for Continual Audio-Visual Learning
build_optimizer_and_scheduler_adam_v2 1 other paper
1 later
2309.05281 (2023-09)
Class-Incremental Grouping Network for Continual Audio-Visual Learning
concat_all_gather 1 other paper
1 the same month
2209.13583 (2022-09)
Learning State-Aware Visual Representations from Audible Interactions
visualize 1 other paper
1 later
2309.05281 (2023-09)
Class-Incremental Grouping Network for Continual Audio-Visual Learning

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

Audio-visual source localization is a challenging task that aims to predict the location of visual sound sources in a video. Since collecting ground-truth annotations of sounding objects can be costly, a plethora of weakly-supervised localization methods that can learn from datasets with no bounding-box annotations have been proposed in recent years, by leveraging the natural co-occurrence of audio and visual signals. Despite significant interest, popular evaluation protocols have two major flaws. First, they allow for the use of a fully annotated dataset to perform early stopping, thus significantly increasing the annotation effort required for training. Second, current evaluation metrics assume the presence of sound sources at all times. This is of course an unrealistic assumption, and thus better metrics are necessary to capture the model's performance on (negative) samples with no visible sound sources. To accomplish this, we extend the test set of popular benchmarks, Flickr SoundNet and VGG-Sound Sources, in order to include negative samples, and measure performance using metrics that balance localization accuracy and recall. Using the new protocol, we conducted an extensive evaluation of prior methods, and found that most prior works are not capable of identifying negatives and suffer from significant overfitting problems (rely heavily on early stopping for best results). We also propose a new approach for visual sound source localization that addresses both these problems. In particular, we found that, through extreme visual dropout and the use of momentum encoders, the proposed approach combats overfitting effectively, and establishes a new state-of-the-art performance on both Flickr SoundNet and VGG-Sound Source. Code and pre-trained models are available at https://github.com/stoneMo/SLAVC.

For agents

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

get_harvested_code_for_paper("2209.09634")
get_code_for_paper("2209.09634")
have("2209.09634")

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

curl https://syntology.ai/api/ran/2209.09634.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.09634.svg)](https://syntology.ai/paper/2209.09634)

Connect an agent — have() is free.