SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08139 · 2020

Interactive Video Object Segmentation Using Global and Local Transfer Modules

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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 12 have no contract verdict; 0 failures of our instrument; 3 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/2007.08139.json · badge: /api/ran/2007.08139.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
yuk6heo/IVOS-ATNet canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
dongkwonjin/Semantic-Line-SLNet community (classifier label)
classifier basis not recorded on the link
9 ran · 3 no recorded run
FunctionStatusWhere it lives
apply_pad Ran
ran on a synthesized input
yuk6heo/IVOS-ATNet/libs/utils.py
code served (permissive licence) · get_code("066a8b05ecbb3bce")
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. 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 numpy as np

# Test case 1: 2D grayscale image with explicit padinfo
img_2d = np.random.rand(28, 35)
padinfo_explicit = ((2, 3), (4, 5))

# Test case 2: 3D color image without padinfo (auto-calculation)
img_3d = np.random.rand(50, 60, 3)
padinfo_none = None

# We need to provide one set of arguments - using 3D image without padinfo
# to test the auto-padding logic
ARGS = {
    "img": img_3d,
    "padinfo": padinfo_none
}
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 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
combine_masks_with_batch Ran
ran on a synthesized input
yuk6heo/IVOS-ATNet/libs/utils_torch.py
code served (permissive licence) · get_code("2724e0efd0bcfecf")
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 4, dtype family float, shape (2, 1, 4, 5) as a later run recorded it. 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, 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 masks tensor with shape [B, nobj, H, W]
# B=2 (batch size), nobj=3 (number of objects), H=4, W=5
masks = torch.rand(2, 3, 4, 5)

# Number of objects
n_obj = 3

# Threshold for mask probability
th = 0.5

# Whether to return as one-hot encoding
return_as_onehot = False

ARGS = {
    "masks": masks,
    "n_obj": n_obj,
    "th": th,
    "return_as_onehot": return_as_onehot,
}
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 4, dtype family float, shape (2, 1, 4, 5) — shape (2, 1, 4, 5) 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
divided_region_mask Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/evaluation/eval_func.py
code served (permissive licence) · get_code("ebe6247047d4ec42")
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 4, dtype family float, shape (2, 2, 60, 40) as a later run recorded it. 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, 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)

# line_pts should be a tensor with shape (line_num, 4)
# Each row represents [x1, y1, x2, y2] coordinates of a line
# We'll create 2 lines for testing
line_pts = torch.tensor([
    [10.0, 20.0, 10.0, 50.0],  # vertical line
    [5.0, 15.0, 25.0, 35.0]     # diagonal line
], dtype=torch.float32)

# size should be a tuple or list representing (width, height)
size = (40, 60)

ARGS = {
    'line_pts': line_pts,
    'size': size
}
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 Tensor, ndim 4, dtype family float, shape (2, 2, 60, 40) — shape (2, 2, 60, 40) 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
eval_AUC_A Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/evaluation/eval_process.py
code served (permissive licence) · get_code("a7ab087a5808adf4")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. 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, 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 torch.nn as nn

torch.manual_seed(0)

class MockEvalFunc:
    def measure_miou(self, out, gt):
        # Returns a tuple (miou_value, something_else)
        # miou_value should be a float
        return 0.75, None
    
    def calculate_AUC(self, miou, metric):
        # Takes miou dict and metric string, returns AUC value
        return 0.85

# Create tiny tensors for out and gt
out = [
    torch.randn(2, 4),
    torch.randn(2, 4)
]

gt = [
    torch.randn(2, 4),
    torch.randn(2, 4)
]

eval_func = MockEvalFunc()

ARGS = {
    'out': out,
    'gt': gt,
    'eval_func': eval_func
}
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 float, ndim 0, dtype family float, shape () — shape () 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
eval_AUC_PR Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/evaluation/eval_process.py
code served (permissive licence) · get_code("5737458ee1231106")
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)

class MockEvalFunc:
    def measure_miou(self, out, gt):
        # Returns two tensors: miou for precision and recall
        # out shape: (out_num,), gt shape: (gt_num,)
        out_num = out.shape[0]
        gt_num = gt.shape[0]
        miou_p = torch.rand(out_num, dtype=torch.float32)
        miou_r = torch.rand(gt_num, dtype=torch.float32)
        return miou_p, miou_r
    
    def matching(self, miou, idx):
        # Takes miou dict and index, returns match_p and match_r
        # miou['p'][idx] and miou['r'][idx] contain tensors
        p_tensor = miou['p'][idx]
        r_tensor = miou['r'][idx]
        match_p = p_tensor
        match_r = r_tensor
        return match_p, match_r
    
    def calculate_AUC(self, miou, metric):
        # Takes miou dict (which is actually match dict) and metric string
        # Returns a scalar AUC value
        if metric == 'precision':
            all_values = []
            for idx in miou['p']:
                all_values.append(miou['p'][idx])
            if all_values:
                return float(torch.cat(all_values).mean())
            return 0.0
        elif metric == 'recall':
            all_values = []
            for idx in miou['r']:
                all_values.append(miou['r'][idx])
            if all_values:
                return float(torch.cat(all_values).mean())
            return 0.0
        return 0.0

# Create sample out and gt as lists of tensors
out = [
    torch.rand(4, 3),  # 4 detections, 3 features
    torch.rand(2, 3),  # 2 detections, 3 features
]

gt = [
    torch.rand(3, 3),  # 3 ground truth, 3 features
    torch.rand(5, 3),  # 5 ground truth, 3 features
]

eval_func = MockEvalFunc()

ARGS = {
    'out': out,
    'gt': gt,
    'eval_func': eval_func,
}
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
get_prop_list Ran
ran on a synthesized input
yuk6heo/IVOS-ATNet/libs/utils.py
code served (permissive licence) · get_code("bfb32f8653031cfa")
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 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 torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - annotated_frames: list of integers (frame indices), used with .count(), .remove(), .reverse(), .index()
# - annotated_now: integer (current frame index)
# - num_frames: integer (total number of frames)
# - proportion: float (default 1.0), used in comparison and multiplication
# - get_close_anno_frames: boolean (default False), used in conditional

# Build valid arguments
ARGS = {
    "annotated_frames": [5, 10, 15, 20, 25],  # List of annotated frame indices
    "annotated_now": 15,                       # Current annotated frame
    "num_frames": 30,                          # Total frames in video
    "proportion": 0.8,                         # Proportion of range to include
    "get_close_anno_frames": False             # Whether to return close frames info
}
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 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
measure_IoU Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/evaluation/eval_func.py
code served (permissive licence) · get_code("cd5023b2159c5f4c")
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 2, 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)

# X1 and X2 are binary masks that will be added together
# The function expects tensors with shape (batch_size, height, width)
# Operations: addition, comparison (!=0, ==2), sum over dims (1,2)

X1 = torch.randint(0, 2, (2, 4, 3), dtype=torch.float32)
X2 = torch.randint(0, 2, (2, 4, 3), dtype=torch.float32)

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
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
measure_IoU_set Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/evaluation/eval_func.py
code served (permissive licence) · get_code("bbab9f755a20036f")
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, 3) as a later run recorded it. 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, 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 small binary mask tensors
# ref_mask: shape (ref_num, 2, height, width) - 2 channels, binary masks
# tar_mask: shape (tar_num, 2, height, width) - 2 channels, binary masks

ref_num = 3
tar_num = 2
height = 4
width = 4

# Create random binary masks (0 or 1)
ref_mask = torch.randint(0, 2, (ref_num, 2, height, width), dtype=torch.float32)
tar_mask = torch.randint(0, 2, (tar_num, 2, height, width), dtype=torch.float32)

ARGS = {
    "ref_mask": ref_mask,
    "tar_mask": tar_mask,
}
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, 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
non_maximum_suppression Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/modules.py
code served (permissive licence) · get_code("1952b3a21e3326a1")
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 1, dtype family float, shape (2,) as a later run recorded it. 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, 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)

# The function expects:
# - score: a 1D tensor of scores for each mask
# - mask: a 3D tensor of shape (num_masks, 2, height, width) containing binary masks
# - thresd: a threshold value (float)

num_masks = 2
height = 4
width = 3

# Create score tensor - 1D tensor with scores for each mask
score = torch.tensor([0.9, 0.7], dtype=torch.float32)

# Create mask tensor - shape (num_masks, 2, height, width)
# Each mask has 2 channels (for the two mask comparisons in the function)
mask = torch.randint(0, 2, (num_masks, 2, height, width), dtype=torch.float32)

# Threshold value for NMS
thresd = 0.5

ARGS = {
    'score': score,
    'mask': mask,
    'thresd': thresd
}
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 1, dtype family float, shape (2,) — shape (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
to_np Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/utils.py
code served (permissive licence) · get_code("90d5599d1ec3e4be")
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 torch

torch.manual_seed(0)

# The function to_np takes a tensor with a .cpu() method and converts it to numpy
# Create a small tensor on CPU
data = torch.randn(2, 4)

ARGS = {
    'data': data
}
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 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
to_np2 Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/utils.py
code served (permissive licence) · get_code("595a24f015a16800")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a small tensor on CPU
tensor_data = torch.randn(2, 4)

ARGS = {
    "data": tensor_data
}
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 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
to_tensor Ran
ran on a synthesized input
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/utils.py
code served (permissive licence) · get_code("60217905378521fd")
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. 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, 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 'data' parameter that is a numpy array
# It will call torch.from_numpy(data) and then .cuda()
# We need to provide a numpy array (CPU only - don't call .cuda() ourselves)

data = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    'data': data
}
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 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
prepare_model Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/prepare.py
code served (permissive licence) · get_code("2cdc3d3a4b27f434")
How it ran

no invocation recorded.

save_model_max Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/save_model.py
code served (permissive licence) · get_code("839736fe2e2c99ea")
How it ran

no invocation recorded.

save_model_max_upper Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Semantic-Line-SLNet/Modelling/code/libs/save_model.py
code served (permissive licence) · get_code("5b352c4c9fc41c5a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 12 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
to_np 1 other paper
1 later
2203.15302 (2022-03)
Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
to_np2 1 other paper
1 later
2203.15302 (2022-03)
Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
to_tensor 1 other paper
1 later
2203.15302 (2022-03)
Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes

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

An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. We develop a deep neural network, which consists of the annotation network (A-Net) and the transfer network (T-Net). First, given user scribbles on a frame, A-Net yields a segmentation result based on the encoder-decoder architecture. Second, T-Net transfers the segmentation result bidirectionally to the other frames, by employing the global and local transfer modules. The global transfer module conveys the segmentation information in an annotated frame to a target frame, while the local transfer module propagates the segmentation information in a temporally adjacent frame to the target frame. By applying A-Net and T-Net alternately, a user can obtain desired segmentation results with minimal efforts. We train the entire network in two stages, by emulating user scribbles and employing an auxiliary loss. Experimental results demonstrate that the proposed interactive video object segmentation algorithm outperforms the state-of-the-art conventional algorithms. Codes and models are available at https://github.com/yuk6heo/IVOS-ATNet.

For agents

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

get_harvested_code_for_paper("2007.08139")
get_code_for_paper("2007.08139")
have("2007.08139")

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

curl https://syntology.ai/api/ran/2007.08139.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.08139.svg)](https://syntology.ai/paper/2007.08139)

Connect an agent — have() is free.