SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.06592 · 2021

Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 5 have no contract verdict; 1 failure of our instrument; 2 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/2107.06592.json · badge: /api/ran/2107.06592.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
TaoRuijie/TalkNet_ASD canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
taoruijie/talknet-asd canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
jiang-yidi/ts-talknet extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
bb_intersection_over_union Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
taoruijie/talknet-asd/demoTalkNet.py
code served (permissive licence) · get_code("8388af70b8314436")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float, 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 computes Intersection over Union (IoU) between two bounding boxes
# Each box is represented as [x1, y1, x2, y2] where (x1,y1) is top-left and (x2,y2) is bottom-right
# boxA and boxB should be sequences/lists of 4 numeric values

boxA = [10, 20, 50, 80]
boxB = [30, 40, 70, 100]
evalCol = False

ARGS = {
    "boxA": boxA,
    "boxB": boxB,
    "evalCol": evalCol
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
eq Ran
ran on a synthesized input
TaoRuijie/TalkNet_ASD/utils/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
face_similarity Ran
ran, honoured the contract we drafted
jiang-yidi/ts-talknet/data_prep/face_enroll_speech.py
pointer only (licence: NONE) · get_code("d464e211ddc0306e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiang-yidi/ts-talknet 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.

init_args Ran
ran on a synthesized input
TaoRuijie/TalkNet_ASD/utils/tools.py
code served (permissive licence) · get_code("2699b09938d17ce7")
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 Args. 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

class Args:
    pass

# Create a temporary directory for the test
temp_dir = tempfile.mkdtemp()

args = Args()
args.savePath = os.path.join(temp_dir, 'save')
args.dataPathAVA = os.path.join(temp_dir, 'data_ava')
args.evalDataType = 'val'

ARGS = {'args': args}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, pandas, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Args — a Args output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Args output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_csv Ran
ran on a synthesized input
TaoRuijie/TalkNet_ASD/utils/get_ava_active_speaker_performance.py
code served (permissive licence) · get_code("bdc52ecccc77b9e1")
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()
temp_filename = os.path.join(temp_dir, "test_data.csv")

# Write a small CSV with the columns that the function expects
csv_content = """frame_timestamp,entity_id,value
2023-01-01 10:00:00,entity_001,100
2023-01-01 10:01:00,entity_002,200
"""

with open(temp_filename, 'w') as f:
    f.write(csv_content)

# Define the arguments
ARGS = {
    'filename': temp_filename,
    'column_names': ['frame_timestamp', 'entity_id', 'value']
}
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
read_LRS3_ST Ran
ran on a synthesized input
TaoRuijie/TalkNet_ASD/TalkSet/generate_TalkSet.py
code served (permissive licence) · get_code("32296f4ba3756725")
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 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 tempfile
import os

# Create a temporary file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_lrs3.txt")

# Write some test lines to the file
with open(temp_file, 'w') as f:
    for i in range(40000):  # Write more than 30000 lines to test the slicing
        f.write(f"line {i}\n")

ARGS = {
    'file': temp_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 list, ndim 1, dtype family float — 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
read_Vox_lines Ran
ran on a synthesized input
TaoRuijie/TalkNet_ASD/TalkSet/generate_TalkSet.py
code served (permissive licence) · get_code("0d9dbc902b34db85")
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 tempfile
import os

# Create a temporary file with test data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("1 This is a line starting with 1\n")
temp_file.write("0 This is a line starting with 0\n")
temp_file.write("1 Another line starting with 1\n")
temp_file.write("0 Another line starting with 0\n")
temp_file.close()

ARGS = {
    'file': temp_file.name
}
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 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
compute_average_precision Not yet run
unverified (harvested, no recorded run)
TaoRuijie/TalkNet_ASD/utils/get_ava_active_speaker_performance.py
code served (permissive licence) · get_code("2e0a799ccbd489e7")
How it ran

no invocation recorded.

get_length Not yet run
unverified (harvested, no recorded run)
TaoRuijie/TalkNet_ASD/TalkSet/generate_TalkSet.py
code served (permissive licence) · get_code("f460ba227a983282")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
compute_average_precision 11 other papers
2 dated earlier, 9 later
aaai_6793 (2020 (year only))
Background Suppression Network for Weakly-Supervised Temporal Action Localization
2006.07976 (2020-06)
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
and 8 more not named here
eq 2 other papers
1 dated earlier, 1 later
aaai_6793 (2020 (year only))
Background Suppression Network for Weakly-Supervised Temporal Action Localization
aaai_19900 (2022 (year only))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
bb_intersection_over_union 1 other paper
1 later
2209.04355 (2022-09)
MIntRec: A New Dataset for Multimodal Intent Recognition

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

Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechanism for inter-modality interaction, and a self-attention mechanism to capture long-term speaking evidence. The experiments demonstrate that TalkNet achieves 3.5% and 2.2% improvement over the state-of-the-art systems on the AVA-ActiveSpeaker dataset and Columbia ASD dataset, respectively. Code has been made available at: https://github.com/TaoRuijie/TalkNet_ASD.

For agents

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

get_harvested_code_for_paper("2107.06592")
get_code_for_paper("2107.06592")
have("2107.06592")

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

curl https://syntology.ai/api/ran/2107.06592.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.06592.svg)](https://syntology.ai/paper/2107.06592)

Connect an agent — have() is free.