SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_6793 · AAAI · 2020

Background Suppression Network for Weakly-Supervised Temporal Action Localization

Youngjung Uh, Pilhyeon Lee, Hyeran Byun

Open in the Atlas

Code that ran

13 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; 1 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 4 failures of our instrument; 7 no recorded run), 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/aaai_6793.json · badge: /api/ran/aaai_6793.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
activitynet/ActivityNet canonical (classifier label)
classifier basis: census
8 ran · 5 no recorded run
Pilhyeon/BaSNet-pytorch canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
construct_video_filename Ran
ran on a synthesized input
activitynet/ActivityNet/Crawler/Kinetics/download.py
code served (permissive licence) · get_code("f63c95a08c681174")
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 str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os

# Construct a valid row dictionary with required keys
row = {
    'video-id': 'vid_001',
    'start-time': 120,
    'end-time': 480,
    'label-name': 'action'
}

# Construct label_to_dir as a dictionary mapping label names to directories
label_to_dir = {
    'action': '/output/action',
    'other': '/output/other'
}

# trim_format parameter with default value
trim_format = '%06d'

ARGS = {
    'row': row,
    'label_to_dir': label_to_dir,
    'trim_format': trim_format
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
create_video_folders Ran
ran on a synthesized input
activitynet/ActivityNet/Crawler/Kinetics/download.py
code served (permissive licence) · get_code("a567d38032983a36")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import pandas as pd

# Create a temporary directory for testing
tmpdir = tempfile.mkdtemp()
output_dir = os.path.join(tmpdir, 'output')
tmp_dir = os.path.join(tmpdir, 'tmp')

# Create a dataset with label-name column
dataset_with_labels = pd.DataFrame({
    'label-name': ['cat', 'dog', 'cat', 'bird', 'dog'],
    'data': [1, 2, 3, 4, 5]
})

# Create a dataset without label-name column
dataset_without_labels = pd.DataFrame({
    'data': [1, 2, 3, 4, 5],
    'other_col': ['a', 'b', 'c', 'd', 'e']
})

ARGS = {
    'dataset': dataset_with_labels,
    'output_dir': output_dir,
    'tmp_dir': tmp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
download_clip Ran
ran on a synthesized input
activitynet/ActivityNet/Crawler/Kinetics/download.py
code served (permissive licence) · get_code("d4f9303d2178d062")
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 tempfile

ARGS = {
    'video_identifier': 'dQw4w9WgXcQ',  # Valid 11-character YouTube ID format
    'output_filename': '/tmp/output_video.mp4',  # Path where output will be stored
    'start_time': 10.5,  # Start trimming at 10.5 seconds
    'end_time': 30.2,  # End trimming at 30.2 seconds
    'tmp_dir': '/tmp/kinetics',  # Temporary directory for downloads
    'num_attempts': 5,  # Number of retry attempts
    'url_base': 'https://www.youtube.com/watch?v='  # YouTube base URL
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
eq Ran
ran on a synthesized input
activitynet/ActivityNet/Evaluation/get_ava_active_speaker_performance.py
code served (permissive licence) · get_code("080a23995e2591f0")
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 bool, ndim 0, dtype family float, 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 eq compares two values and checks if their absolute difference
# is within a tolerance. It works with numeric types (int, float, etc.)
# We need to provide two numeric values and optionally a tolerance parameter.

# Simple numeric values that are approximately equal
a = 1.0
b = 1.0000000001
tolerance = 1e-09

ARGS = {
    "a": a,
    "b": b,
    "tolerance": tolerance
}
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 bool, 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
get_proposal_oic Ran
ran on a synthesized input
Pilhyeon/BaSNet-pytorch/utils.py
code served (permissive licence) · get_code("ae4b3e9bc417c98a")
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. 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

# Construct minimal valid arguments for get_proposal_oic

# tList: list of arrays, where each contains indices
# For len(tList)=2, each element should be array-like with shape (1, N) where N varies
tList = [
    np.array([[0, 1, 2, 5, 6]]),  # First element: grouped indices, some consecutive
    np.array([[1, 2, 3, 4]])       # Second element: grouped indices
]

# wtcam: 3D array accessed as wtcam[indices, i, 0]
# Shape: (num_frames, len(tList), 1)
# num_frames should be at least max(tList values) + 1
wtcam = np.random.rand(10, 2, 1)

# final_score: 1D array accessed as final_score[c_pred[i]]
# Length should be at least max(c_pred) + 1
final_score = np.array([0.5, 0.7, 0.9, 0.6])

# c_pred: 1D array of class predictions, length = len(tList)
# Values should be valid indices into final_score
c_pred = np.array([0, 2])

# scale: scalar, used in computation
scale = 8

# v_len: video length in frames
v_len = 100

# sampling_frames: number of sampled frames
sampling_frames = 4

# num_segments: number of segments
num_segments = 5

# lambda_: expansion factor for outer region
lambda_ = 0.25

# gamma: weighting factor for final_score
gamma = 0.2

ARGS = {
    "tList": tList,
    "wtcam": wtcam,
    "final_score": final_score,
    "c_pred": c_pred,
    "scale": scale,
    "v_len": v_len,
    "sampling_frames": sampling_frames,
    "num_segments": num_segments,
    "lambda_": lambda_,
    "gamma": gamma
}
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 list — a list 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
init_args Ran
ran on a synthesized input
Pilhyeon/BaSNet-pytorch/options.py
code served (permissive licence) · get_code("0e6118fe56644429")
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 SimpleNamespace. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
from types import SimpleNamespace

# Create temporary directories for the test
temp_base = tempfile.mkdtemp()
model_path = os.path.join(temp_base, "models")
log_path = os.path.join(temp_base, "logs")
output_path = os.path.join(temp_base, "outputs")

# Create a SimpleNamespace object with the required attributes
args = SimpleNamespace(
    model_path=model_path,
    log_path=log_path,
    output_path=output_path
)

ARGS = {"args": args}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleNamespace — a SimpleNamespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleNamespace 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
interpolated_prec_rec Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Pilhyeon/BaSNet-pytorch/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.

load_csv Ran
ran; our contract draft was wrong, not the code
activitynet/ActivityNet/Evaluation/get_ava_active_speaker_performance.py
code served (permissive licence) · get_code("2b0fca044dd4be81")
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 DataFrame. 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 pandas as pd
import tempfile
import os

# Create a temporary CSV file with the required columns
temp_dir = tempfile.gettempdir()
filename = os.path.join(temp_dir, 'test_data.csv')

# Write test CSV data with frame_timestamp and entity_id columns
csv_data = """2023-01-01 10:00:00,entity_1,value1
2023-01-01 10:00:01,entity_2,value2"""

with open(filename, 'w') as f:
    f.write(csv_data)

# Define column names that match the CSV structure
column_names = ['frame_timestamp', 'entity_id', 'data_value']

ARGS = {
    'filename': filename,
    'column_names': column_names
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
make_image_key Ran
ran on a synthesized input
activitynet/ActivityNet/Evaluation/get_ava_performance.py
code served (permissive licence) · get_code("4c6224ef80a79273")
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 str. 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 decimal

def make_image_key(video_id, timestamp):
    """Returns a unique identifier for a video id & timestamp."""
    return '%s,%.6f' % (video_id, decimal.Decimal(timestamp))

ARGS = {
    'video_id': 'video_12345',
    'timestamp': 42.123456789
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
read_csv Ran
ran; our contract draft was wrong, not the code
activitynet/ActivityNet/Evaluation/get_ava_performance.py
code served (permissive licence) · get_code("87c68435a43b253f")
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 io
import csv
import logging

# Configure logging
logging.basicConfig(level=logging.INFO)

# Create a sample CSV file in memory with AVA format
csv_content = """video1,0.5
video1,0.5,0.1,0.2,0.3,0.4,1,0.9
video1,0.5,0.15,0.25,0.35,0.45,2,0.85
video2,1.0
video2,1.0,0.2,0.3,0.4,0.5,1,0.95
video2,1.0,0.25,0.35,0.45,0.55,3
"""

csv_file = io.StringIO(csv_content)
csv_file.name = "test.csv"

# Create a class whitelist - set of valid action IDs
class_whitelist = {1, 2, 3}

# Capacity limit for boxes per example
capacity = 5

ARGS = {
    'csv_file': csv_file,
    'class_whitelist': class_whitelist,
    'capacity': capacity,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
read_labelmap Ran
ran; our contract draft was wrong, not the code
activitynet/ActivityNet/Evaluation/get_ava_performance.py
code served (permissive licence) · get_code("642a0fed989fffb5")
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 io

# Create a valid labelmap file content
labelmap_content = """item {
  name: "background"
  id: 0
}
item {
  name: "person"
  id: 1
}
item {
  name: "car"
  label_id: 2
}
"""

# Create a file-like object from the string
labelmap_file = io.StringIO(labelmap_content)

ARGS = {
    'labelmap_file': labelmap_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
segment_iou Ran
ran, honoured the contract we drafted
Pilhyeon/BaSNet-pytorch/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.

upgrade_resolution Ran
ran on a synthesized input
Pilhyeon/BaSNet-pytorch/utils.py
code served (permissive licence) · get_code("a6b6f459b6b264bb")
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 (10,) 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.interpolate import interp1d

# Construct test data for upgrade_resolution function
# The function takes:
# - arr: a numpy array (used with .shape[0] and passed to interp1d)
# - scale: a numeric scale factor (used in division 1/scale)

# Create a small 1D array as input
arr = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

# Create a scale factor
scale = 2

ARGS = {
    'arr': arr,
    'scale': scale
}
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 (10,) — shape (10,) 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
compute_average_precision Not yet run
unverified (harvested, no recorded run)
activitynet/ActivityNet/Evaluation/get_ava_active_speaker_performance.py
code served (permissive licence) · get_code("b2d77ad898044477")
How it ran

no invocation recorded.

compute_average_precision_detection Not yet run
unverified (harvested, no recorded run)
Pilhyeon/BaSNet-pytorch/eval/eval_detection.py
code served (permissive licence) · get_code("7be4ca6a451d8384")
How it ran

no invocation recorded.

crosscheck_videos Not yet run
unverified (harvested, no recorded run)
activitynet/ActivityNet/Crawler/run_crosscheck.py
code served (permissive licence) · get_code("475dd6657a3a9a10")
How it ran

no invocation recorded.

get_blocked_videos Not yet run
unverified (harvested, no recorded run)
Pilhyeon/BaSNet-pytorch/eval/utils_eval.py
code served (permissive licence) · get_code("a01a64a508273392")
How it ran

no invocation recorded.

get_status_and_reason Not yet run
unverified (harvested, no recorded run)
activitynet/ActivityNet/Crawler/Kinetics/process_download_report.py
code served (permissive licence) · get_code("cc8273c957278eb5")
How it ran

no invocation recorded.

process_download_report Not yet run
unverified (harvested, no recorded run)
activitynet/ActivityNet/Crawler/Kinetics/process_download_report.py
code served (permissive licence) · get_code("49ddb12c1fc59cf2")
How it ran

no invocation recorded.

wrapper_process_download_reports Not yet run
unverified (harvested, no recorded run)
activitynet/ActivityNet/Crawler/Kinetics/process_download_report.py
code served (permissive licence) · get_code("b3a338c34360cf40")
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, 12 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 12 later) and 8 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
interpolated_prec_rec 13 other papers
4 dated earlier, 9 later
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
4 dated earlier, 9 later
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
compute_average_precision 11 other papers
10 later, 1 same year, order not determinable
2006.07976 (2020-06)
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
2107.06592 (2021-07)
Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
and 8 more not named here
compute_average_precision_detection 4 other papers
1 dated earlier, 3 later
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
aaai_16280 (2021 (year only))
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
and 1 more not named here
get_blocked_videos 4 other papers
1 dated earlier, 3 later
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
aaai_16280 (2021 (year only))
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
136640190 (2022 (year only))
Dual-Evidential Learning for Weakly-supervised Temporal Action Localization
and 1 more not named here
eq 2 other papers
2 later
2107.06592 (2021-07)
Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
init_args 1 other paper
1 later
aaai_16280 (2021 (year only))
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
load_csv 1 other paper
1 later
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
make_image_key 1 other paper
1 later
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
read_csv 1 other paper
1 later
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
read_labelmap 1 other paper
1 later
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
upgrade_resolution 1 other paper
1 later
aaai_16280 (2021 (year only))
Weakly-supervised Temporal Action Localization by Uncertainty Modeling

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 is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-theart methods on the most popular benchmarks -THUMOS'14 and ActivityNet. Our code and the trained model are available at https://github.com/Pilhyeon/BaSNet-pytorch.

For agents

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

get_harvested_code_for_paper("aaai_6793")
get_code_for_paper("aaai_6793")
have("aaai_6793")

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

curl https://syntology.ai/api/ran/aaai_6793.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_6793.svg)](https://syntology.ai/paper/aaai_6793)

Connect an agent — have() is free.