SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.04838 · 2020

TransNet V2: An effective deep network architecture for fast shot transition detection

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 1 failure of our instrument; 2 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/2008.04838.json · badge: /api/ran/2008.04838.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
soCzech/TransNetV2 canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
shallwe999/TransNetV2-SBD-Visualize community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
check_and_fix_dicts Ran
ran on a synthesized input
soCzech/TransNetV2/inference-pytorch/convert_weights.py
code served (permissive licence) · get_code("7af38278c93d587f")
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

torch.manual_seed(0)

# The function checks if keys in torch_dict exist in tf_dict
# and if shapes match between tf_dict tensors and torch_dict shape tuples.
# It also handles 'num_batches_tracked' specially.

# tf_dict should map strings to torch tensors with shape attributes
# torch_dict should map strings to shape tuples

tf_dict = {
    'weight': torch.randn(4, 3),
    'bias': torch.randn(3),
    'num_batches_tracked': torch.tensor(1.0, dtype=torch.float32),
}

torch_dict = {
    'weight': (4, 3),
    'bias': (3,),
    'num_batches_tracked': (1,),
}

ARGS = {
    'tf_dict': tf_dict,
    'torch_dict': torch_dict,
}
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 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
compute_normalization_fixed_point Ran
ran on a synthesized input
soCzech/TransNetV2/training/bi_tempered_loss.py
code served (permissive licence) · get_code("cec13b69d85253c3")
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 EagerTensor, ndim 2, dtype family float, shape (2, 1) 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 tensorflow as tf
import numpy as np

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

# Create small test tensors
batch_size = 2
num_classes = 4

# activations: shape (batch_size, num_classes) - logits or pre-softmax activations
activations = tf.constant([
    [1.0, 2.0, 3.0, 0.5],
    [0.5, 1.5, 2.5, 1.0]
], dtype=tf.float32)

# t: Temperature parameter (> 1.0 for tail heaviness)
t = tf.constant(1.5, dtype=tf.float32)

# num_iters: Number of fixed-point iterations
num_iters = 5

ARGS = {
    "activations": activations,
    "t": t,
    "num_iters": num_iters
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) 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
evaluate_scenes Ran
ran on a synthesized input
soCzech/TransNetV2/training/metrics_utils.py
code served (permissive licence) · get_code("8b38bd5a0be9bce7")
How it ran

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

import numpy as np

# Create small test data for ground truth and predicted scenes
# gt_scenes and pred_scenes should be numpy arrays of shape (n_scenes, 2)
# where each row is [start_frame, end_frame]

gt_scenes = np.array([
    [0, 5],
    [6, 9],
    [10, 15]
], dtype=np.int32)

pred_scenes = np.array([
    [0, 5],
    [6, 9],
    [10, 15]
], dtype=np.int32)

ARGS = {
    "gt_scenes": gt_scenes,
    "pred_scenes": pred_scenes,
    "return_mistakes": False,
    "n_frames_miss_tolerance": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
exp_t Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
soCzech/TransNetV2/training/bi_tempered_loss.py
code served (permissive licence) · get_code("a6d36281c438e25b")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small test tensors
u = tf.constant([[0.5, -0.3, 1.2, -0.8],
                 [0.1, 0.9, -0.5, 0.4]], dtype=tf.float32)

# Test case 1: t != 1.0 (uses _internal_exp_t)
t_val = tf.constant(0.5, dtype=tf.float32)

ARGS = {
    "u": u,
    "t": t_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
get_batches Ran
ran on a synthesized input
soCzech/TransNetV2/training/evaluate.py
code served (permissive licence) · get_code("7d243f22f59049e3")
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 generator. 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

# Create a small test frames array
# The function expects frames to be a numpy array with shape (n_frames, ...)
# Looking at the function, it concatenates frames along axis 0
frames = np.random.randn(47, 8, 3)  # 47 frames with shape (8, 3) each

ARGS = {
    "frames": frames
}
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 generator — a generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a generator 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_scenes_from_transition_frames Ran
ran on a synthesized input
soCzech/TransNetV2/training/consolidate_datasets.py
code served (permissive licence) · get_code("a574b706c69a2e4a")
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 int, shape (5, 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

ARGS = {
    "transition_frames": np.array([5, 12, 25, 40]),
    "video_len": 50
}
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 int, shape (5, 2) — shape (5, 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
log_t Ran
ran on a synthesized input
soCzech/TransNetV2/training/bi_tempered_loss.py
code served (permissive licence) · get_code("e047237f9926614c")
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 EagerTensor, ndim 1, dtype family float, shape (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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Create small test tensors
u = tf.constant([1.5, 2.0, 3.0, 4.5], dtype=tf.float32)
t = tf.constant(0.5, dtype=tf.float32)

ARGS = {
    "u": u,
    "t": t,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float, shape (4,) — shape (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
predictions_to_scenes Ran
ran on a synthesized input
soCzech/TransNetV2/training/metrics_utils.py
code served (permissive licence) · get_code("3da0df168740c1aa")
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 int, 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

# The function predictions_to_scenes takes a single parameter: predictions
# It iterates through predictions, treating each element as 0 or 1
# and identifies scenes (contiguous regions) based on transitions
# So predictions should be an array-like of binary values (0s and 1s)

# Create a simple predictions array with some transitions
predictions = np.array([0, 0, 1, 1, 1, 0, 0, 1, 1, 0], dtype=np.int32)

ARGS = {
    "predictions": predictions
}
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 int, 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
read_predictions Ran
ran on a synthesized input
shallwe999/TransNetV2-SBD-Visualize/utils.py
code served (permissive licence) · get_code("fa843917bfca3cfb")
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 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 prediction data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("0.5 0.3\n")
temp_file.write("0.7 0.2\n")
temp_file.write("0.1 0.9\n")
temp_file.close()

file_name = temp_file.name

ARGS = {
    'file_name': file_name,
    'split_char': ' '
}
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 2, 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_scenes Ran
ran on a synthesized input
shallwe999/TransNetV2-SBD-Visualize/utils.py
code served (permissive licence) · get_code("732def07b44046eb")
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 2, 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 tempfile
import os

# Create a temporary file with scene data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("1 10\n")
temp_file.write("2 20\n")
temp_file.write("3 30\n")
temp_file.close()

ARGS = {
    'file_name': temp_file.name,
    'split_char': ' '
}
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 2, 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
remap_name Ran
ran on a synthesized input
soCzech/TransNetV2/inference-pytorch/convert_weights.py
code served (permissive licence) · get_code("61c9ba481effd824")
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

torch.manual_seed(0)

def remap_name(x):
    x = x.replace('TransNet/', '')
    l = []
    for a in x.split('/'):
        if a.startswith('SDDCNN') or a.startswith('DDCNN'):
            a = a.split('_')
            a = a[0] + '.' + str(int(a[1]) - 1)
        elif a == 'conv_spatial':
            a = 'layers.0'
        elif a == 'conv_temporal':
            a = 'layers.1'
        elif a == 'kernel:0' or a == 'gamma:0':
            a = 'weight'
        elif a == 'bias:0' or a == 'beta:0':
            a = 'bias'
        elif a == 'dense':
            a = 'fc1'
        elif a == 'dense_1':
            a = 'cls_layer1'
        elif a == 'dense_2':
            a = 'cls_layer2'
        elif a == 'dense_3':
            a = 'frame_sim_layer.projection'
        elif a == 'dense_4':
            a = 'frame_sim_layer.fc'
        elif a == 'dense_5':
            a = 'color_hist_layer.fc'
        elif a == 'FrameSimilarity' or a == 'ColorHistograms':
            a = ''
        elif a == 'moving_mean:0':
            a = 'running_mean'
        elif a == 'moving_variance:0':
            a = 'running_var'
        l.append(a)
    x = '.'.join([a for a in l if a != ''])
    return x

ARGS = {
    'x': 'TransNet/SDDCNN_1/conv_spatial/kernel:0'
}
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
remap_tensor Ran
ran on a synthesized input
soCzech/TransNetV2/inference-pytorch/convert_weights.py
code served (permissive licence) · get_code("c35a46af5bf2323c")
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 5, dtype family float, shape (6, 5, 2, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Test case 1: 5D tensor
x_5d = torch.randn(2, 3, 4, 5, 6)

# Test case 2: 2D tensor
x_2d = torch.randn(2, 3)

# We'll use the 5D tensor as the primary test case
ARGS = {
    "x": x_5d
}
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 5, dtype family float, shape (6, 5, 2, 3, 4) — shape (6, 5, 2, 3, 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
scenes2zero_one_representation Ran
ran on a synthesized input
soCzech/TransNetV2/training/create_dataset.py
code served (permissive licence) · get_code("4f1f9a4527adf939")
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 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 numpy as np

# Construct valid arguments for scenes2zero_one_representation
ARGS = {
    "scenes": [(0, 10), (15, 25), (30, 40)],
    "n_frames": 50
}
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 int — 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
graph Not yet run
unverified (harvested, no recorded run)
soCzech/TransNetV2/training/metrics_utils.py
code served (permissive licence) · get_code("c19395bc49d7798c")
How it ran

no invocation recorded.

main_process Not yet run
unverified (harvested, no recorded run)
shallwe999/TransNetV2-SBD-Visualize/transnetv2.py
code served (permissive licence) · get_code("e6c126c38a88b3c8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
predictions_to_scenes 3 other papers
2 dated earlier, 1 later
1911.06644 (2019-11)
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
1911.07559 (2019-11)
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
2106.13230 (2021-06)
Video Swin Transformer
exp_t 1 other paper
1 dated earlier
1909.05829 (2019-09)
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
get_batches 1 other paper
1 later
2304.06116 (2023-04)
AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection

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

Although automatic shot transition detection approaches are already investigated for more than two decades, an effective universal human-level model was not proposed yet. Even for common shot transitions like hard cuts or simple gradual changes, the potential diversity of analyzed video contents may still lead to both false hits and false dismissals. Recently, deep learning-based approaches significantly improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data. Nevertheless, one hundred percent accuracy is still an unreachable ideal. In this paper, we share the current version of our deep network TransNet V2 that reaches state-of-the-art performance on respected benchmarks. A trained instance of the model is provided so it can be instantly utilized by the community for a highly efficient analysis of large video archives. Furthermore, the network architecture, as well as our experience with the training process, are detailed, including simple code snippets for convenient usage of the proposed model and visualization of results.

For agents

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

get_harvested_code_for_paper("2008.04838")
get_code_for_paper("2008.04838")
have("2008.04838")

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

curl https://syntology.ai/api/ran/2008.04838.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.04838.svg)](https://syntology.ai/paper/2008.04838)

Connect an agent — have() is free.