SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.13675 · 2021

Weakly-guided Self-supervised Pretraining for Temporal Activity Detection

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 3 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/2111.13675.json · badge: /api/ran/2111.13675.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
kkahatapitiya/SSDet canonical (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
accimage_loader Ran
ran on a synthesized input
kkahatapitiya/SSDet/kinetics.py
code served (permissive licence) · get_code("a44afb1c0019609f")
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 Image. 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 tempfile
import os
from PIL import Image as PILImage

# Create a temporary directory and a valid test image
temp_dir = tempfile.mkdtemp()
test_image_path = os.path.join(temp_dir, "test_image.jpg")

# Create a simple RGB image and save it
img = PILImage.new('RGB', (4, 3), color=(255, 0, 0))
img.save(test_image_path)

# Define ARGS with the path parameter
ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
conv1x1x1 Ran
ran on a synthesized input
kkahatapitiya/SSDet/x3d.py
code served (permissive licence) · get_code("559e7247652ccade")
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 Conv3d. 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)

ARGS = {
    'in_planes': 3,
    'out_planes': 16,
    'stride': 1,
    'task': 'loc'
}
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 Conv3d — a Conv3d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv3d 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
equalize Ran
ran on a synthesized input
kkahatapitiya/SSDet/transforms/spatial_transforms.py
code served (permissive licence) · get_code("7b28778e776afc65")
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 3, dtype family int, shape (3, 4, 5) 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
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a valid torch.uint8 tensor image with shape [3, H, W] (3 channels, height, width)
# This satisfies the requirement: [..., 1 or 3, H, W] format with 3 dimensions
img_tensor = torch.randint(0, 256, (3, 4, 5), dtype=torch.uint8)

ARGS = {
    "img": img_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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 3, dtype family int, shape (3, 4, 5) — shape (3, 4, 5) 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_inplanes Ran
ran, honoured the contract we drafted
kkahatapitiya/SSDet/x3d.py
code served (permissive licence) · get_code("acfa08610335818d")
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 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function get_inplanes takes a version parameter and returns a list of tuples
# based on the version key ('S', 'M', or 'XL')
# The function only uses the version parameter to index into a dictionary

ARGS = {
    'version': 'S'
}
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 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
load_value_file Ran
ran on a synthesized input
kkahatapitiya/SSDet/kinetics.py
code served (permissive licence) · get_code("4a7c82f20a853d09")
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 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 tempfile
import os

# Create a temporary file with a float value
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write('42.5\n')
temp_file.close()

file_path = temp_file.name

ARGS = {
    'file_path': file_path
}
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 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
pil_loader Ran
ran, honoured the contract we drafted
kkahatapitiya/SSDet/kinetics.py
pointer only (licence: MIT); the stored copy get_code serves, from YuemingJin/MTRCNet-CL, is pointer only (licence: NONE) · get_code("1df9a5ffd9b38c34")
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 YuemingJin/MTRCNet-CL, 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.

tensor_equalize Ran
ran on a synthesized input
kkahatapitiya/SSDet/transforms/spatial_transforms.py
code served (permissive licence) · get_code("d88ae1104c961f9f")
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 3, dtype family int, shape (3, 4, 5) 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)

# Create a valid 3D image tensor (single image)
# Shape: (C, H, W) where C=3 channels, H=4, W=5
img_3d = torch.randint(0, 256, (3, 4, 5), dtype=torch.uint8)

ARGS = {
    "img": img_3d
}
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 3, dtype family int, shape (3, 4, 5) — shape (3, 4, 5) 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
video_loader Ran
ran on a synthesized input
kkahatapitiya/SSDet/charades.py
code served (permissive licence) · get_code("47b8813afb1b73cb")
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 4, 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 os
import tempfile
from PIL import Image
import numpy as np

# Create a temporary directory structure with dummy image files
temp_dir = tempfile.mkdtemp()
video_name = "test_video"
video_dir = os.path.join(temp_dir, video_name)
os.makedirs(video_dir, exist_ok=True)

# Create a few dummy jpg files
for i in range(3):
    img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
    img = Image.fromarray(img_array)
    img_path = os.path.join(video_dir, f"{video_name}-{str(i).zfill(6)}.jpg")
    img.save(img_path)

# Define a simple image loader function
def image_loader(image_path):
    img = Image.open(image_path)
    return np.array(img)

ARGS = {
    "video_dir_path": temp_dir,
    "vid": video_name,
    "frame_indices": [0, 1, 2],
    "image_loader": image_loader
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 4, 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
accimage_loader Not yet run
unverified (harvested, no recorded run)
kkahatapitiya/SSDet/charades.py
code served (permissive licence) · get_code("aae0a4f3535e8f26")
How it ran

no invocation recorded.

conv3x3x3 Not yet run
unverified (harvested, no recorded run)
kkahatapitiya/SSDet/x3d.py
code served (permissive licence) · get_code("553378f88d6b728a")
How it ran

no invocation recorded.

pil_equalize Not yet run
unverified (harvested, no recorded run)
kkahatapitiya/SSDet/transforms/spatial_transforms.py
code served (permissive licence) · get_code("ee0f6cebf82a264a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 7 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
pil_loader 28 other papers
16 dated earlier, 12 later
1702.00758 (2017-02)
HashNet: Deep Learning to Hash by Continuation
1805.07932 (2018-05)
Bilinear Attention Networks
1807.06587 (2018-07)
Deep Exemplar-based Colorization
and 25 more not named here
accimage_loader 3 other papers
2 dated earlier, 1 later
1912.05534 (2019-12)
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
2009.09805 (2020-09)
Active Contrastive Learning of Audio-Visual Video Representations
aaai_25362 (2023 (year only))
Global-Local Characteristic Excited Cross-Modal Attacks from Images to Videos
get_inplanes 2 other papers
2 dated earlier
1912.00998 (2019-12)
A Multigrid Method for Efficiently Training Video Models
2004.04730 (2020-04)
X3D: Expanding Architectures for Efficient Video Recognition
load_value_file 1 other paper
1 dated earlier
2006.15731 (2020-06)
Unsupervised Learning of Video Representations via Dense Trajectory Clustering

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

Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the scale of detection datasets is limited. Thus, commonly, previous work on temporal activity detection resorts to fine-tuning a classification model pretrained on large-scale classification datasets (e.g., Kinetics-400). However, such pretrained models are not ideal for downstream detection, due to the disparity between the pretraining and the downstream fine-tuning tasks. In this work, we propose a novel 'weakly-guided self-supervised' pretraining method for detection. We leverage weak labels (classification) to introduce a self-supervised pretext task (detection) by generating frame-level pseudo labels, multi-action frames, and action segments. Simply put, we design a detection task similar to downstream, on large-scale classification data, without extra annotations. We show that the models pretrained with the proposed weakly-guided self-supervised detection task outperform prior work on multiple challenging activity detection benchmarks, including Charades and MultiTHUMOS. Our extensive ablations further provide insights on when and how to use the proposed models for activity detection. Code is available at https://github.com/kkahatapitiya/SSDet.

For agents

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

get_harvested_code_for_paper("2111.13675")
get_code_for_paper("2111.13675")
have("2111.13675")

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

curl https://syntology.ai/api/ran/2111.13675.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.13675.svg)](https://syntology.ai/paper/2111.13675)

Connect an agent — have() is free.