SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1406.2199 · 2014

Two-Stream Convolutional Networks for Action Recognition in Videos

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 3 have no contract verdict; 2 failures 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/1406.2199.json · badge: /api/ran/1406.2199.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
woodfrog/ActionRecognition community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
Michaelgod/test reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
jerryljq/ActionRecognition reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
conv_block Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
woodfrog/ActionRecognition/models/resnet50.py
code served (permissive licence) · get_code("5e7a557c615eb17e")
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 KerasTensor. 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 tensorflow as tf
from keras import layers
from keras.layers import Activation, Conv2D, BatchNormalization
import keras.backend as K

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

# Create a small input tensor
# Shape: (batch_size=2, height=4, width=4, channels=3)
input_tensor = tf.keras.Input(shape=(4, 4, 3))

# Define parameters
kernel_size = 3
filters = [64, 64, 256]  # filters1, filters2, filters3
stage = 3
block = 'a'
strides = (2, 2)

ARGS = {
    'input_tensor': input_tensor,
    'kernel_size': kernel_size,
    'filters': filters,
    'stage': stage,
    'block': block,
    'strides': strides
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor 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
decode_prediction Ran
ran; our contract draft was wrong, not the code
Michaelgod/test/predict.py
pointer only (licence: GPL-3.0) · get_code("fc2bbda446121dde")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Michaelgod/test, is not in the permissive set Syntology serves inline. 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.

preprocess_input Ran
ran on a synthesized input
woodfrog/ActionRecognition/rnn_practice/LRCN/imagenet_utils.py
code served (permissive licence) · get_code("b1aaeed051544edb")
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 4, dtype family float, shape (2, 4, 5, 3) 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
import torch

# The function expects a 4D numpy tensor (batch, channels, height, width) or (batch, height, width, channels)
# Let's create a small batch of images: batch_size=2, channels=3, height=4, width=5
# Using channels_last format (batch, height, width, channels)
x = np.random.rand(2, 4, 5, 3).astype(np.float32) * 255

ARGS = {
    "x": x,
    "data_format": "channels_last"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, 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 4, dtype family float, shape (2, 4, 5, 3) — shape (2, 4, 5, 3) 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
preprocess_single_frame Ran
ran on a synthesized input
woodfrog/ActionRecognition/predict.py
code served (permissive licence) · get_code("4953cb1be1c7abc8")
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 3, dtype family float, shape (4, 3, 3) 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

def preprocess_single_frame(frame):
    from keras.applications.imagenet_utils import preprocess_input
    frame = preprocess_input(frame)
    frame /= 255
    return frame

# Create a small stand-in frame as a numpy array
# The function expects an image-like array that can be processed by keras preprocess_input
# Typically this is shape (height, width, channels) with uint8 or float values
frame = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

ARGS = {
    "frame": frame
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 3) 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
temporal_CNN Ran
ran on a synthesized input
woodfrog/ActionRecognition/models/temporal_CNN.py
code served (permissive licence) · get_code("0e464771c030663d")
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 Functional. 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

ARGS = {
    'input_shape': (224, 224, 2),
    'classes': 101,
    'weights_dir': '/nonexistent/path/that/does/not/exist.h5',
    'include_top': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
decode_prediction Not yet run
unverified (harvested, no recorded run)
jerryljq/ActionRecognition/predict.py
pointer only (licence: NONE) · get_code("c064c9e4cc5ca645")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jerryljq/ActionRecognition 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. No invocation recorded.

identity_block Not yet run
unverified (harvested, no recorded run)
woodfrog/ActionRecognition/models/resnet50.py
code served (permissive licence) · get_code("4679231cd26e9089")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
conv_block 3 other papers
3 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.03287 (2018-06)
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
1912.07160 (2019-12)
DAmageNet: A Universal Adversarial Dataset
identity_block 3 other papers
3 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.03287 (2018-06)
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
1912.07160 (2019-12)
DAmageNet: A Universal Adversarial Dataset

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

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multi-task learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.

For agents

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

get_harvested_code_for_paper("1406.2199")
get_code_for_paper("1406.2199")
have("1406.2199")

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

curl https://syntology.ai/api/ran/1406.2199.json

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

[![Syntology run record](https://syntology.ai/api/ran/1406.2199.svg)](https://syntology.ai/paper/1406.2199)

Connect an agent — have() is free.