SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 136640190 · ECCV · 2022

Dual-Evidential Learning for Weakly-supervised Temporal Action Localization

Junyu Gao, Shicai Yang, Changsheng Xu, Mengyuan Chen

Open in the Atlas

Code that ran

19 of 20 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; 5 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 4 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; 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/136640190.json · badge: /api/ran/136640190.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
MengyuanChen21/ECCV2022-DELU canonical (classifier label)
classifier basis: census
19 ran · 1 no recorded run
FunctionStatusWhere it lives
sigmoid_rampup Ran
ran, honoured the contract we drafted
MengyuanChen21/ECCV2022-DELU/utils/wsad_utils.py
code served (permissive licence) · get_code("3fb68ed6809a8085")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:27:05Z). 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

# The function sigmoid_rampup takes two parameters:
# - current: a numeric value representing the current step/epoch
# - rampup_length: a numeric value representing the total rampup length

ARGS = {
    "current": 5,
    "rampup_length": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — 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
cosine_rampdown Ran
ran, honoured the contract we drafted
MengyuanChen21/ECCV2022-DELU/utils/wsad_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from atinghosh/Adverserial-VAE, is pointer only (licence: NONE) · get_code("214e4ee9afcfa0e3")
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 atinghosh/Adverserial-VAE, 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.

exp_evidence Ran
ran; our contract draft was wrong, not the code
MengyuanChen21/ECCV2022-DELU/edl_loss.py
code served (permissive licence) · get_code("ddba7773fd3d51f7")
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)

# The function exp_evidence takes a single parameter y and applies torch.exp and torch.clamp to it
# y should be a tensor
y = torch.randn(2, 4)

ARGS = {
    "y": y
}
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
filter_segments Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/proposal_methods.py
code served (permissive licence) · get_code("bd92b5e18d57194d")
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 (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
import pandas as pd

# Create small test data for segment_predict
# This should be a 2D array where each row contains [start_frame, end_frame]
segment_predict = np.array([
    [10, 20],
    [50, 60],
    [100, 110]
], dtype=np.float32)

# Create a video name string
vn = "test_video_001"

ARGS = {
    "segment_predict": segment_predict,
    "vn": vn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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 (3, 2) — shape (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
filter_segments Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/detectionMAP.py
code served (permissive licence) · get_code("7758772e75188f8a")
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 1, dtype family float, shape (0,) 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 segment_predict: shape (2, 3) where columns are [video_idx, start, end]
segment_predict = np.array([
    [0, 10, 20],  # video 0, frames 10-20
    [1, 5, 15]    # video 1, frames 5-15
], dtype=float)

# Construct videonames: list mapping video indices to video names
videonames = ["video_A", "video_B"]

# Construct ambilist: list of tuples (videoname, _, start_time, end_time)
# The function multiplies start/end times by factor to get frame ranges
ambilist = [
    ("video_A", "dummy", 1.0, 2.5),  # video_A: frames 10-25 at factor=10
    ("video_B", "dummy", 0.5, 1.0)   # video_B: frames 5-10 at factor=10
]

# Construct factor: multiplier for converting time to frames
factor = 10

ARGS = {
    "segment_predict": segment_predict,
    "videonames": videonames,
    "ambilist": ambilist,
    "factor": factor
}
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 1, dtype family float, shape (0,) — shape (0,) 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
filter_segments Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/eval_anno_file_generation.py
code served (permissive licence) · get_code("0f811328c955b307")
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 (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 pandas as pd

# Construct arguments for filter_segments

# segment_predict: numpy array with shape (num_segments, 3)
# columns are: [video_index, start_frame, end_frame]
segment_predict = np.array([
    [0, 100, 150],
    [1, 200, 250],
    [0, 300, 350],
], dtype=float)

# videonames: list of video names indexed by video_index
videonames = ["video_1.mp4", "video_2.mp4"]

# ambilist: list of ambiguous segments, each entry is [videoname, ?, start_time, end_time]
# The function checks if predicted segments overlap with ambiguous segments
ambilist = [
    ["video_1.mp4", "dummy", 4.0, 6.0],  # corresponds to frames 100-150 at 25fps, 16 denominator
    ["video_2.mp4", "dummy", 8.0, 10.0],  # corresponds to frames 200-250
]

ARGS = {
    "segment_predict": segment_predict,
    "videonames": videonames,
    "ambilist": ambilist,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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 (3, 3) — shape (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
getAP Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/classificationMAP.py
code served (permissive licence) · get_code("227942c6bc7e435b")
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

# Construct valid arguments for getAP function
# The function expects:
# - conf: array of confidence scores (float values between 0 and 1)
# - labels: array of binary labels (0 or 1)

# Create confidence scores and labels
np.random.seed(0)
conf = np.array([0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2], dtype='float32')
labels = np.array([1, 1, 0, 1, 0, 1, 0, 0], dtype='int32')

ARGS = {
    'conf': conf,
    'labels': labels
}
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
getClassificationMAP Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/classificationMAP.py
code served (permissive licence) · get_code("b0f04cc9e7b36e90")
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

# Set random seed for reproducibility
np.random.seed(0)

# Create small sample data
n_samples = 5
n_labels = 3

# confidence: n_samples x n_labels matrix of confidence scores (floats between 0 and 1)
confidence = np.random.rand(n_samples, n_labels).astype('float32')

# labels: n_samples x n_labels matrix of binary labels (0 or 1)
labels = np.random.randint(0, 2, size=(n_samples, n_labels)).astype('int32')

ARGS = {
    "confidence": confidence,
    "labels": labels
}
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_topk_mean Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/proposal_methods.py
code served (permissive licence) · get_code("9fbdd7a234f36fe3")
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 1, dtype family float, shape (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

# Analyze the function:
# - x: array-like that gets sorted along 'axis' and then indexed with [-int(k):, :]
#   This means x must be 2D with shape (N, M) where N is rows and M is columns
# - k: integer (or int-convertible) that specifies how many top elements to take
# - axis: axis along which to sort (default 0)
# The function sorts along axis 0 (rows), takes the last k rows, and means along axis 0

# Create a 2D array with distinct dimensions
x = np.random.randn(5, 3)  # 5 rows, 3 columns
k = 2  # take top 2 rows
axis = 0  # sort along rows

ARGS = {
    "x": x,
    "k": k,
    "axis": axis,
}
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 1, dtype family float, shape (3,) — shape (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
interpolated_prec_rec Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MengyuanChen21/ECCV2022-DELU/eval/utils_eval.py
pointer only (licence: MIT); the stored copy get_code serves, from Ontheway361/BSN_pytorch, is pointer only (licence: NONE) · get_code("81aab88321de62c2")
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 Ontheway361/BSN_pytorch, 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.

linear_rampup Ran
ran, honoured the contract we drafted
MengyuanChen21/ECCV2022-DELU/utils/wsad_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from y-research-sbu/otsurv, is pointer only (licence: NOASSERTION) · get_code("069122bd5268cc56")
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 y-research-sbu/otsurv, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

relu_evidence Ran
ran; our contract draft was wrong, not the code
MengyuanChen21/ECCV2022-DELU/edl_loss.py
code served (permissive licence) · get_code("efecc687b786a0cc")
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
import torch.nn.functional as F

torch.manual_seed(0)

# relu_evidence takes a single parameter y and applies F.relu to it
# y should be a tensor
y = torch.randn(2, 4)

ARGS = {
    "y": y
}
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
segment_iou Ran
ran, honoured the contract we drafted
MengyuanChen21/ECCV2022-DELU/eval/utils_eval.py
pointer only (licence: MIT); the stored copy get_code serves, from Ontheway361/BSN_pytorch, is pointer only (licence: NONE) · get_code("d0744a2fe3151508")
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 Ontheway361/BSN_pytorch, 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.

sigmoid Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/eval_detection.py
code served (permissive licence) · get_code("68a8a4359a62d565")
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

ARGS = {
    "x": np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]),
    "eps": 1e-10
}
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
smooth Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/proposal_methods.py
code served (permissive licence) · get_code("79a000f7e8c93d00")
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 1, dtype family float, shape (12,) 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
from scipy.signal import savgol_filter

# Create a small vector to smooth
v = np.array([1.0, 2.0, 3.0, 2.5, 3.5, 4.0, 3.8, 4.2, 5.0, 4.9, 5.1, 5.5], dtype=float)

ARGS = {
    "v": v,
    "order": 2,
    "lens": 200
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (12,) — shape (12,) 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
smooth Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/detectionMAP.py
code served (permissive licence) · get_code("4a6f77bd7b90ba28")
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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# The function `smooth(v)` takes a parameter `v` and returns it unchanged.
# Since the function body is just `return v`, it accepts any value.
# We'll provide a tensor as the most common use case.

v = torch.randn(2, 4)

ARGS = {
    "v": v
}
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
softplus_evidence Ran
ran; our contract draft was wrong, not the code
MengyuanChen21/ECCV2022-DELU/edl_loss.py
code served (permissive licence) · get_code("f8059bd409d4bdf3")
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
import torch.nn.functional as F

torch.manual_seed(0)

# The function softplus_evidence takes a single parameter y
# and applies F.softplus to it. y should be a tensor.
# Create a small tensor with distinct dimensions for probing
y = torch.randn(2, 4)

ARGS = {
    "y": y
}
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
str2ind Ran
ran on a synthesized input
MengyuanChen21/ECCV2022-DELU/eval/detectionMAP.py
code served (permissive licence) · get_code("165d3974e17f952d")
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 int, ndim 0, dtype family int, shape () 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 str2ind takes a categoryname and classlist
# It searches for the categoryname in classlist and returns the index of the first match

# categoryname should be a string
categoryname = "cat"

# classlist should be a list of strings that can be searched
classlist = ["dog", "cat", "bird", "fish"]

ARGS = {
    "categoryname": categoryname,
    "classlist": classlist,
}
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 int, ndim 0, dtype family int, 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
strlist2indlist Ran
ran, honoured the contract we drafted
MengyuanChen21/ECCV2022-DELU/eval/eval_anno_file_generation.py
code served (permissive licence) · get_code("9ae1a2f9ddf40d14")
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

def str2ind(categoryname, classlist):
    return [i for i in range(len(classlist)) if categoryname == classlist[i]][0]

def strlist2indlist(strlist, classlist):
    return [str2ind(s, classlist) for s in strlist]

# Setup
torch.manual_seed(0)

strlist = ["cat", "dog", "bird"]
classlist = ["cat", "dog", "bird", "fish"]

ARGS = {
    "strlist": strlist,
    "classlist": classlist
}
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 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
get_blocked_videos Not yet run
unverified (harvested, no recorded run)
MengyuanChen21/ECCV2022-DELU/eval/utils_eval.py
code served (permissive licence) · get_code("a01a64a508273392")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 15 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 0 the same month, 9 later) and 5 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
sigmoid_rampup 19 other papers
9 dated earlier, 8 later, 2 same year, order not determinable
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
1904.04717 (2019-04)
Label Propagation for Deep Semi-supervised Learning
1904.09058 (2019-04)
Feature Fusion for Online Mutual Knowledge Distillation
and 16 more not named here
linear_rampup 16 other papers
6 dated earlier, 8 later, 2 same year, order not determinable
1904.04717 (2019-04)
Label Propagation for Deep Semi-supervised Learning
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1911.08177 (2019-11)
Rethinking deep active learning: Using unlabeled data at model training
and 13 more not named here
interpolated_prec_rec 13 other papers
7 dated earlier, 5 later, 1 same year, order not determinable
1804.05113 (2018-04)
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
1806.02964 (2018-06)
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
1907.09702 (2019-07)
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
and 10 more not named here
segment_iou 13 other papers
7 dated earlier, 5 later, 1 same year, order not determinable
1804.05113 (2018-04)
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
1806.02964 (2018-06)
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
1907.09702 (2019-07)
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
and 10 more not named here
cosine_rampdown 12 other papers
6 dated earlier, 6 later
1602.02644 (2016-02)
Generating Images with Perceptual Similarity Metrics based on Deep Networks
1904.04717 (2019-04)
Label Propagation for Deep Semi-supervised Learning
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
and 9 more not named here
exp_evidence 4 other papers
1 dated earlier, 3 later
1806.01768 (2018-06)
Evidential Deep Learning to Quantify Classification Uncertainty
2309.02995 (2023-09)
Continual Evidential Deep Learning for Out-of-Distribution Detection
2405.04405 (2024-05)
Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation
and 1 more not named here
get_blocked_videos 4 other papers
3 dated earlier, 1 later
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
aaai_6793 (2020 (year only))
Background Suppression Network for Weakly-Supervised Temporal Action Localization
aaai_16280 (2021 (year only))
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
and 1 more not named here
relu_evidence 3 other papers
1 dated earlier, 2 later
1806.01768 (2018-06)
Evidential Deep Learning to Quantify Classification Uncertainty
2405.04405 (2024-05)
Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation
2406.07882 (2024-06)
Designing a Dashboard for Transparency and Control of Conversational AI
softplus_evidence 2 other papers
1 dated earlier, 1 later
1806.01768 (2018-06)
Evidential Deep Learning to Quantify Classification Uncertainty
2405.04405 (2024-05)
Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation
filter_segments 1 other paper
1 dated earlier
1807.10418 (2018-07)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
getAP 1 other paper
1 dated earlier
1807.10418 (2018-07)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
getClassificationMAP 1 other paper
1 dated earlier
1807.10418 (2018-07)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
smooth 1 other paper
1 dated earlier
1807.10418 (2018-07)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
str2ind 1 other paper
1 dated earlier
1807.10418 (2018-07)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
strlist2indlist 1 other paper
1 dated earlier
1807.10418 (2018-07)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification

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

Weakly-supervised temporal action localization (WS-TAL) aims to localize the action instances and recognize their categories with only video-level labels. Despite great progress, existing methods suffer from severe action-background ambiguity, which mainly comes from background noise introduced by aggregation operations and large intraaction variations caused by the task gap between classification and localization. To address this issue, we propose a generalized evidential deep learning (EDL) framework for WS-TAL, called Dual-Evidential Learning for Uncertainty modeling (DELU), which extends the traditional paradigm of EDL to adapt to the weakly-supervised multi-label classification goal. Specifically, targeting at adaptively excluding the undesirable background snippets, we utilize the video-level uncertainty to measure the interference of background noise to video-level prediction. Then, the snippet-level uncertainty is further deduced for progressive learning, which gradually focuses on the entire action instances in an "easy-tohard" manner. Extensive experiments show that DELU achieves stateof-the-art performance on THUMOS14 and ActivityNet1.2 benchmarks. Our code is available in github.com/MengyuanChen21/ECCV2022-DELU.

For agents

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

get_harvested_code_for_paper("136640190")
get_code_for_paper("136640190")
have("136640190")

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

curl https://syntology.ai/api/ran/136640190.json

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

[![Syntology run record](https://syntology.ai/api/ran/136640190.svg)](https://syntology.ai/paper/136640190)

Connect an agent — have() is free.