SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.07984 · 2020

Leveraging Category Information for Single-Frame Visual Sound Source Separation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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 7 have no contract verdict; 3 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/2007.07984.json · badge: /api/ran/2007.07984.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
ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
ly-zhu/Separating-Sounds-from-a-Single-Image community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
FunctionStatusWhere it lives
load_checkpoint Ran
ran; our contract draft was wrong, not the code
ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation/main_Appearance_Sound.py
code served (permissive licence) · get_code("18a0f2d0f82fbfea")
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) and returned tuple. 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 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
import tempfile
import os

torch.manual_seed(0)

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

net_sound = MinimalNet()
net_frame = MinimalNet()
nets = (net_sound, net_frame)

# Create optimizer
optimizer = torch.optim.Adam(
    list(net_sound.parameters()) + list(net_frame.parameters()),
    lr=0.001
)

# Create history dict with validation error
history = {
    'val': {
        'err': [0.5, 0.3, 0.2]
    }
}

# Create a temporary checkpoint file
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, 'checkpoint_latest.pth')

# Save a valid checkpoint
state = {
    'epoch': 5,
    'state_dict_net_sound': net_sound.state_dict(),
    'state_dict_net_frame': net_frame.state_dict(),
    'optimizer': optimizer.state_dict(),
    'history': history
}
torch.save(state, checkpoint_path)

ARGS = {
    'nets': nets,
    'optimizer': optimizer,
    'history': history,
    'filename': checkpoint_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
load_checkpoint Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/main_Appearance_att_Sound.py
code served (permissive licence) · get_code("7eaee91dfd40b5ae")
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
import tempfile
import os

torch.manual_seed(0)

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

net_sound = MinimalNet()
net_frame = MinimalNet()
net_avol = MinimalNet()

# Create optimizer
optimizer = torch.optim.Adam(
    list(net_sound.parameters()) + 
    list(net_frame.parameters()) + 
    list(net_avol.parameters()),
    lr=0.001
)

# Create history dict matching what the function expects
history = {
    'train': {'loss': [0.5, 0.4]},
    'val': {'err': [0.3, 0.25]}
}

# Create a temporary checkpoint file
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, 'test_checkpoint.pth')

# Save a valid checkpoint to load
state = {
    'epoch': 5,
    'state_dict_net_sound': net_sound.state_dict(),
    'state_dict_net_frame': net_frame.state_dict(),
    'state_dict_net_avol': net_avol.state_dict(),
    'optimizer': optimizer.state_dict(),
    'history': history
}
torch.save(state, checkpoint_path)

ARGS = {
    'net_sound': net_sound,
    'net_frame': net_frame,
    'net_avol': net_avol,
    'optimizer': optimizer,
    'history': history,
    'filename': checkpoint_path
}
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
load_checkpoint Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/main_CatEmb_Sound.py
code served (permissive licence) · get_code("42b20e91f34ebe8b")
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
import tempfile
import os

torch.manual_seed(0)

# Create a simple neural network
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create instances
net = SimpleNet()
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)
history = {
    'val': {
        'err': [0.5, 0.3, 0.2]
    }
}

# Create a temporary directory for checkpoint file
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, 'checkpoint_latest.pth')

# Create a valid checkpoint file by calling torch.save with proper structure
state = {
    'epoch': 5,
    'state_dict_net_sound': net.state_dict(),
    'optimizer': optimizer.state_dict(),
    'history': history
}
torch.save(state, checkpoint_path)

# Define ARGS for load_checkpoint function
ARGS = {
    'nets': SimpleNet(),
    'optimizer': torch.optim.SGD(SimpleNet().parameters(), lr=0.01),
    'history': {'val': {'err': []}},
    'filename': checkpoint_path
}
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
load_checkpoint_from_train Ran
ran; our contract draft was wrong, not the code
ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation/main_Appearance_Sound.py
code served (permissive licence) · get_code("5b434cdece8b83b2")
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) 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 torch.nn as nn
import tempfile
import os

torch.manual_seed(0)

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

net_sound = MinimalNet()
net_frame = MinimalNet()

nets = (net_sound, net_frame)

# Create a temporary checkpoint file
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, 'checkpoint_latest.pth')

# Create and save a valid checkpoint
optimizer = torch.optim.Adam(list(net_sound.parameters()) + list(net_frame.parameters()))
history = {
    'val': {
        'err': [0.5, 0.3, 0.2]
    }
}
epoch = 10

state = {
    'epoch': epoch,
    'state_dict_net_sound': net_sound.state_dict(),
    'state_dict_net_frame': net_frame.state_dict(),
    'optimizer': optimizer.state_dict(),
    'history': history
}
torch.save(state, checkpoint_path)

ARGS = {
    'nets': nets,
    'filename': checkpoint_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
load_checkpoint_from_train Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/main_Appearance_att_Sound.py
code served (permissive licence) · get_code("fe139af98f1594db")
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 os
import torch
import torch.nn as nn

# Create minimal nn.Module instances that have state_dict() method
class SimpleNet(nn.Module):
    def __init__(self, input_dim=4, output_dim=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

torch.manual_seed(0)

# Create three minimal networks
net_sound = SimpleNet(input_dim=4, output_dim=3)
net_frame = SimpleNet(input_dim=5, output_dim=2)
net_avol = SimpleNet(input_dim=6, output_dim=1)

# Create a filename for the checkpoint
checkpoint_filename = '/tmp/test_checkpoint.pth'

# Create a checkpoint file by first saving one
optimizer = torch.optim.Adam(
    list(net_sound.parameters()) + 
    list(net_frame.parameters()) + 
    list(net_avol.parameters()),
    lr=0.001
)

history = {
    'train': {'loss': [0.5, 0.4], 'err': [0.1, 0.08]},
    'val': {'loss': [0.6, 0.5], 'err': [0.12, 0.1]}
}

# Create args object for saving
class Args:
    def __init__(self):
        self.ckpt = '/tmp'
        self.best_err = float('inf')

args = Args()

# Save a checkpoint first so we can load it
state = {
    'epoch': 5,
    'state_dict_net_sound': net_sound.state_dict(),
    'state_dict_net_frame': net_frame.state_dict(),
    'state_dict_net_avol': net_avol.state_dict(),
    'optimizer': optimizer.state_dict(),
    'history': history
}
os.makedirs('/tmp', exist_ok=True)
torch.save(state, checkpoint_filename)

# Define ARGS for load_checkpoint_from_train function
ARGS = {
    'net_sound': net_sound,
    'net_frame': net_frame,
    'net_avol': net_avol,
    'filename': checkpoint_filename
}
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
load_checkpoint_from_train Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/main_CatEmb_Sound.py
code served (permissive licence) · get_code("5f67e6f9050256f6")
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 SimpleNet. 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
import os
import tempfile

torch.manual_seed(0)

# Create a minimal nn.Module that has load_state_dict and state_dict methods
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create the net
net_sound = SimpleNet()

# Create a checkpoint file to load from
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, 'test_checkpoint.pth')

# Create a valid checkpoint state
state = {
    'epoch': 5,
    'state_dict_net_sound': net_sound.state_dict(),
    'optimizer': torch.optim.Adam(net_sound.parameters()).state_dict(),
    'history': {'val': {'err': [0.5, 0.4, 0.3]}}
}

# Save the checkpoint
torch.save(state, checkpoint_path)

ARGS = {
    'nets': net_sound,
    'filename': checkpoint_path
}
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 SimpleNet — a SimpleNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleNet 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
magnitude2heatmap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ly-zhu/Separating-Sounds-from-a-Single-Image/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from weiguoPian/ContAV-Sep_NeurIPS2024, is pointer only (licence: NONE) · get_code("e52e3c5bf79fea6f")
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 weiguoPian/ContAV-Sep_NeurIPS2024, 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.

recover_rgb Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/utils.py
code served (permissive licence) · get_code("5dce17dfe9cd12fe")
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, 5, 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 torch
import numpy as np

torch.manual_seed(0)

# The function expects img to be a tensor with shape (C, H, W)
# where C=3 (for RGB), and it iterates over the first dimension
# It calls .mul_(), .add_(), .cpu(), .numpy(), and .transpose()
img = torch.randn(3, 4, 5)

ARGS = {
    "img": img
}
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 ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
unet_conv Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/models/audio_net.py
code served (permissive licence) · get_code("a707c39dcde29fcc")
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 Sequential. 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 = {
    "input_nc": 3,
    "output_nc": 64,
    "innermost": False,
    "outermost": False,
    "norm_layer": nn.BatchNorm2d,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
unet_upconv Ran
ran on a synthesized input
ly-zhu/Separating-Sounds-from-a-Single-Image/models/audio_net.py
code served (permissive licence) · get_code("bf4439e420654360")
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 Sequential. 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 = {
    "input_nc": 64,
    "output_nc": 32,
    "outermost": False,
    "norm_layer": nn.BatchNorm2d
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
warpgrid Ran
ran, honoured the contract we drafted
ly-zhu/Separating-Sounds-from-a-Single-Image/utils.py
code served (permissive licence) · get_code("a4a08206de81190b")
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 4, dtype family float, shape (2, 4, 3, 2) 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

# Construct arguments for warpgrid function
bs = 2  # batch size
HO = 4  # output height
WO = 3  # output width
warp = True  # apply warping transformation

ARGS = {
    "bs": bs,
    "HO": HO,
    "WO": WO,
    "warp": warp
}
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 4, dtype family float, shape (2, 4, 3, 2) — shape (2, 4, 3, 2) 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
convert_to_separable_conv Not yet run
unverified (harvested, no recorded run)
ly-zhu/Separating-Sounds-from-a-Single-Image/models/_deeplab.py
code served (permissive licence) · get_code("ce942a958c0ae909")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 9 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
convert_to_separable_conv 10 other papers
2 dated earlier, 8 later
1706.05587 (2017-06)
Rethinking Atrous Convolution for Semantic Image Segmentation
1905.03561 (2019-05)
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
and 7 more not named here
warpgrid 6 other papers
1 dated earlier, 5 later · 2 only as an assembly brick
1908.11602 (2019-08)
Recursive Visual Sound Separation Using Minus-Plus Net
2210.16472 (2022-10)
Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation
2212.07065 (2022-12)
CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
and 3 more not named here
magnitude2heatmap 1 other paper
1 later
2411.02860 (2024-11)
Continual Audio-Visual Sound Separation

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

Visual sound source separation aims at identifying sound components from a given sound mixture with the presence of visual cues. Prior works have demonstrated impressive results, but with the expense of large multi-stage architectures and complex data representations (e.g. optical flow trajectories). In contrast, we study simple yet efficient models for visual sound separation using only a single video frame. Furthermore, our models are able to exploit the information of the sound source category in the separation process. To this end, we propose two models where we assume that i) the category labels are available at the training time, or ii) we know if the training sample pairs are from the same or different category. The experiments with the MUSIC dataset show that our model obtains comparable or better performance compared to several recent baseline methods. The code is available at https://github.com/ly-zhu/Leveraging-Category-Information-for-Single-Frame-Visual-Sound-Source-Separation

For agents

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

get_harvested_code_for_paper("2007.07984")
get_code_for_paper("2007.07984")
have("2007.07984")

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

curl https://syntology.ai/api/ran/2007.07984.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.07984.svg)](https://syntology.ai/paper/2007.07984)

Connect an agent — have() is free.