SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.07976 · 2020

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

arXiv · PDF · Open in the Atlas

Code that ran

17 of 27 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; 2 honoured the contract we drafted, 1 violated it and 10 have no contract verdict; 4 failures of our instrument; 10 no recorded run), measured 2026-11-21; 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/2006.07976.json · badge: /api/ran/2006.07976.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
Siyu-C/ACAR-Net canonical (classifier label)
classifier basis: census
12 ran · 9 no recorded run
salmank255/ROADSlowFast community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
area Ran
ran on a synthesized input
Siyu-C/ACAR-Net/ava_evaluation/np_box_list_ops.py
code served (permissive licence) · get_code("ae6e56e979816086")
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; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:27Z. 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

class BoxList:
    """Stand-in BoxList class that holds box coordinates."""
    def __init__(self, y_min, x_min, y_max, x_max):
        self.y_min = y_min
        self.x_min = x_min
        self.y_max = y_max
        self.x_max = x_max
    
    def get_coordinates(self):
        """Returns box coordinates as (y_min, x_min, y_max, x_max)."""
        return self.y_min, self.x_min, self.y_max, self.x_max

torch.manual_seed(0)

# Create a BoxList with 2 boxes
y_min = np.array([1.0, 2.0])
x_min = np.array([1.0, 2.0])
y_max = np.array([5.0, 6.0])
x_max = np.array([4.0, 7.0])

boxlist = BoxList(y_min, x_min, y_max, x_max)

ARGS = {
    "boxlist": boxlist
}
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 1, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
ava_pose_softmax_criterion Ran
ran on a synthesized input
Siyu-C/ACAR-Net/losses.py
code served (permissive licence) · get_code("3b570b6730c1319f")
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 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects:
# - logits: a tensor of shape (batch_size, num_classes)
#   where num_classes = 13 (pose) + num_interact (interaction classes)
# - targets: a tensor of the same shape as the output of ava_pose_softmax_func
#   which is (batch_size, 13 + num_interact)

batch_size = 2
num_pose_classes = 13
num_interact_classes = 4
total_logits = num_pose_classes + num_interact_classes

# Create logits tensor: (batch_size, 13 + num_interact_classes)
logits = torch.randn(batch_size, total_logits)

# Create targets tensor: same shape as output
# The output is (batch_size, 13 + num_interact_classes)
# with values in [0, 1] due to softmax + sigmoid + clamp
targets = torch.rand(batch_size, total_logits)

ARGS = {
    "logits": logits,
    "targets": targets,
}
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 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
ava_pose_softmax_func Ran
ran on a synthesized input
Siyu-C/ACAR-Net/losses.py
code served (permissive licence) · get_code("b93cca48f0e47db7")
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, 20) 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

torch.manual_seed(0)

# The function takes logits as input
# It expects a tensor with shape (batch_size, num_features)
# where num_features >= 13 (first 13 for pose, rest for interact)
# Let's create a small batch with 20 features total (13 pose + 7 interact)

logits = torch.randn(2, 20)

ARGS = {
    "logits": logits
}
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, 20) — shape (2, 20) 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_precision_recall Ran
ran on a synthesized input
Siyu-C/ACAR-Net/ava_evaluation/metrics.py
code served (permissive licence) · get_code("9faafd74ff0068a0")
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 numpy as np

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

# Create sample data
scores = np.array([0.9, 0.8, 0.7, 0.6, 0.5, 0.4], dtype=np.float32)
labels = np.array([True, True, False, True, False, False], dtype=bool)
num_gt = 4

ARGS = {
    "scores": scores,
    "labels": labels,
    "num_gt": num_gt,
}
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, 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
create_category_index Ran
ran; our contract draft was wrong, not the code
Siyu-C/ACAR-Net/ava_evaluation/label_map_util.py
code served (permissive licence) · get_code("dc6b3dd700e4eea1")
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 torch
import numpy as np

# Based on the function, it expects a list of category dictionaries
# Each dict must have 'id' and 'name' keys
# The function iterates through categories and builds a dict keyed by 'id'

categories = [
    {'id': 1, 'name': 'cat'},
    {'id': 2, 'name': 'dog'},
    {'id': 3, 'name': 'pizza'},
]

ARGS = {
    'categories': categories,
}
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 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
create_logger Ran
ran on a synthesized input
Siyu-C/ACAR-Net/utils.py
code served (permissive licence) · get_code("abf34766c2f1571a")
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 Logger. 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 logging
import tempfile
import os

# Create a temporary file path for the log file
log_file = os.path.join(tempfile.gettempdir(), "test_logger.log")

# Define ARGS with all parameters of create_logger
ARGS = {
    "log_file": log_file,
    "level": logging.INFO,
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
get_area Ran
ran, honoured the contract we drafted
salmank255/ROADSlowFast/kmean_anchors.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from salmank255/ROAD_Waymo_Baseline, is pointer only (licence: NOASSERTION) · get_code("70645db2047d82ec")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from salmank255/ROAD_Waymo_Baseline, 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.

get_center Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
salmank255/ROADSlowFast/kmean_anchors.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from salmank255/ROAD_Waymo_Baseline, is pointer only (licence: NOASSERTION) · get_code("bf09436830878aaa")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from salmank255/ROAD_Waymo_Baseline, 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.

get_env_variable Ran
ran on a synthesized input
Siyu-C/ACAR-Net/distributed_utils.py
code served (permissive licence) · get_code("452dcb1b9317d2d9")
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

# Set up environment variables for testing
os.environ['TEST_VAR_1'] = 'value1'
os.environ['TEST_VAR_2'] = 'value2'

# Define arguments for get_env_variable
ARGS = {
    'variables': ['TEST_VAR_1', 'TEST_VAR_2', 'NONEXISTENT_VAR'],
    'default': None
}
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
get_max_label_map_index Ran
ran, honoured the contract we drafted
Siyu-C/ACAR-Net/ava_evaluation/label_map_util.py
code served (permissive licence) · get_code("d3367980903ee2a9")
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.

# Construct a minimal StringIntLabelMapProto-like object
class LabelMapItem:
    def __init__(self, id_value):
        self.id = id_value

class StringIntLabelMapProto:
    def __init__(self, items):
        self.item = items

# Create label_map with some items having different id values
label_map = StringIntLabelMapProto([
    LabelMapItem(id_value=1),
    LabelMapItem(id_value=5),
    LabelMapItem(id_value=3),
    LabelMapItem(id_value=10),
])

ARGS = {
    "label_map": label_map
}
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 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
get_scheduler Ran
ran on a synthesized input
Siyu-C/ACAR-Net/scheduler.py
code served (permissive licence) · get_code("6ecced1e66623371")
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 StepLRScheduler. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:27Z. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Create a config object for 'step' scheduler
class StepConfig:
    def __init__(self):
        self.type = 'step'
        self.milestone_epochs = [5, 10]
        self.lr_mults = [0.1, 0.1]
        self.base_lr = 0.1
        self.warmup_lr = 0.01
        self.warmup_epochs = 1

step_config = StepConfig()

# Create a config object for 'cosine' scheduler
class CosineConfig:
    def __init__(self):
        self.type = 'cosine'
        self.min_lr = 0.0
        self.base_lr = 0.1
        self.warmup_lr = 0.01
        self.warmup_epochs = 1

cosine_config = CosineConfig()

# Define arguments - test with step scheduler
ARGS = {
    'config': step_config,
    'optimizer': optimizer,
    'n_epochs': 20,
    'epoch_steps': 1
}
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 StepLRScheduler — a StepLRScheduler output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StepLRScheduler output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
Siyu-C/ACAR-Net/calc_mAP.py
code served (permissive licence) · get_code("15e577f3614f1586")
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 torch
import numpy as np

def make_image_key(video_id, timestamp):
    """Returns a unique identifier for a video id & timestamp."""
    return '%s,%04d' % (video_id, int(timestamp))

ARGS = {
    "video_id": "video_001",
    "timestamp": 42.7
}
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 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
parameters_string Ran
ran on a synthesized input
Siyu-C/ACAR-Net/utils.py
code served (permissive licence) · get_code("45a26c192ff99933")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        self.conv1 = nn.Conv1d(2, 5, kernel_size=3)
    
    def forward(self, x):
        return x

module = SimpleModel()

ARGS = {
    'module': module
}
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 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_exclusions Ran
ran on a synthesized input
Siyu-C/ACAR-Net/calc_mAP.py
code served (permissive licence) · get_code("b49799a287ea9eec")
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 set. 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 csv
import io

def make_image_key(video_id, timestamp):
    """Returns a unique identifier for a video id & timestamp."""
    return '%s,%04d' % (video_id, int(timestamp))

# Create a CSV file content as a string
csv_content = """video_001,0123
video_002,0456
video_003,0789"""

# Create a file-like object from the CSV content
exclusions_file = io.StringIO(csv_content)

ARGS = {
    'exclusions_file': exclusions_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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
set_out_video Ran
ran; our contract draft was wrong, not the code
salmank255/ROADSlowFast/inference_vis.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from salmank255/ROAD_Waymo_Baseline, is pointer only (licence: NOASSERTION) · get_code("5040afe356ddac29")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from salmank255/ROAD_Waymo_Baseline, 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.

set_video Ran
ran; our contract draft was wrong, not the code
salmank255/ROADSlowFast/inference_vis.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from salmank255/ROAD_Waymo_Baseline, is pointer only (licence: NOASSERTION) · get_code("21947d8387b20363")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from salmank255/ROAD_Waymo_Baseline, 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.

str2bool Ran
ran, violated the contract we drafted
salmank255/ROADSlowFast/inference_vis.py
code served (permissive licence) · get_code("25c7475539e39da4")
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 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

def str2bool(v):
    return v.lower() in ('yes', 'true', 't', '1')

ARGS = {
    'v': 'true'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
ava_criterion Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/losses.py
code served (permissive licence) · get_code("2751c2cbb8d17356")
How it ran

no invocation recorded.

backbone_models Not yet run
unverified (harvested, no recorded run)
salmank255/ROADSlowFast/models/backbone_models.py
code served (permissive licence) · get_code("5fd8c2cc3399ab75")
How it ran

no invocation recorded.

box_list_to_box_mask_list Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/ava_evaluation/np_box_mask_list_ops.py
code served (permissive licence) · get_code("3a972d2a2de3e7f6")
How it ran

no invocation recorded.

compute_average_precision Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/ava_evaluation/metrics.py
code served (permissive licence) · get_code("029d0444c2c321d4")
How it ran

no invocation recorded.

compute_cor_loc Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/ava_evaluation/metrics.py
code served (permissive licence) · get_code("c0b97624f9249399")
How it ran

no invocation recorded.

convert_label_map_to_categories Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/ava_evaluation/label_map_util.py
code served (permissive licence) · get_code("a5a7cde0ddc2ebbc")
How it ran

no invocation recorded.

init_distributed Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/distributed_utils.py
code served (permissive licence) · get_code("bae310a052f21971")
How it ran

no invocation recorded.

intersection Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/ava_evaluation/np_box_list_ops.py
code served (permissive licence) · get_code("9563a9a954385a6d")
How it ran

no invocation recorded.

iou Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/ava_evaluation/np_box_list_ops.py
code served (permissive licence) · get_code("a7428b0e09d7a2d5")
How it ran

no invocation recorded.

read_csv Not yet run
unverified (harvested, no recorded run)
Siyu-C/ACAR-Net/calc_mAP.py
code served (permissive licence) · get_code("897e38093ca7f101")
How it ran

no invocation recorded.

Also present in other papers' code

Of 27 samples lifted from this paper's linked repositories, 27 carry a function identity and 0 do not. Of the 27 distinct functions with an identity, 10 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 7 later) and 17 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
str2bool 23 other papers
11 dated earlier, 1 the same month, 11 later
1410.5401 (2014-10)
Neural Turing Machines
1502.04623 (2015-02)
DRAW: A Recurrent Neural Network For Image Generation
1504.06852 (2015-04)
FlowNet: Learning Optical Flow with Convolutional Networks
and 20 more not named here
compute_average_precision 11 other papers
10 later, 1 same year, order not determinable
aaai_6793 (2020 (year only))
Background Suppression Network for Weakly-Supervised 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
convert_label_map_to_categories 2 other papers
2 dated earlier
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1812.04960 (2018-12)
Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
create_category_index 2 other papers
2 dated earlier
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1812.04960 (2018-12)
Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
get_area 1 other paper
1 later
2411.01683 (2024-11)
ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving
get_center 1 other paper
1 later
2411.01683 (2024-11)
ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving
get_max_label_map_index 1 other paper
1 dated earlier
1812.04960 (2018-12)
Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
make_image_key 1 other paper
1 later
2106.11310 (2021-06)
Towards Long-Form Video Understanding
set_out_video 1 other paper
1 later
2411.01683 (2024-11)
ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving
set_video 1 other paper
1 later
2411.01683 (2024-11)
ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Localizing persons and recognizing their actions from videos is a challenging task towards high-level video understanding. Recent advances have been achieved by modeling direct pairwise relations between entities. In this paper, we take one step further, not only model direct relations between pairs but also take into account indirect higher-order relations established upon multiple elements. We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context. To this end, we design an Actor-Context-Actor Relation Network (ACAR-Net) which builds upon a novel High-order Relation Reasoning Operator and an Actor-Context Feature Bank to enable indirect relation reasoning for spatio-temporal action localization. Experiments on AVA and UCF101-24 datasets show the advantages of modeling actor-context-actor relations, and visualization of attention maps further verifies that our model is capable of finding relevant higher-order relations to support action detection. Notably, our method ranks first in the AVA-Kineticsaction localization task of ActivityNet Challenge 2020, out-performing other entries by a significant margin (+6.71mAP). Training code and models will be available at https://github.com/Siyu-C/ACAR-Net.

For agents

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

get_harvested_code_for_paper("2006.07976")
get_code_for_paper("2006.07976")
have("2006.07976")

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

curl https://syntology.ai/api/ran/2006.07976.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.07976.svg)](https://syntology.ai/paper/2006.07976)

Connect an agent — have() is free.