SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.02205 · 2020

Deep Multimodal Feature Encoding for Video Ordering

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 failures of our instrument; 0 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/2004.02205.json · badge: /api/ran/2004.02205.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
vivoutlaw/tcbp canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
generate_start_end_index Ran
ran on a synthesized input
vivoutlaw/tcbp/video_ordering_dataset/Audio_Visual_Place_Temporal.py
code served (permissive licence) · get_code("9d2feb13f6fe37e3")
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

ARGS = {
    "last_idx": 100,
    "seg_interval": 20,
    "sub_seg_interval": 5,
}
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
generic_layer_feat_extractor Ran
ran on a synthesized input
vivoutlaw/tcbp/video_ordering_dataset/Audio_Visual_Place_Temporal.py
code served (permissive licence) · get_code("7781eae785554e2e")
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 SimpleModel. 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)

# Create a simple model with named layers
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.fc1 = nn.Linear(4, 3)
        self.fc2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.fc1(x)
        x = self.fc2(x)
        return x

# Instantiate the model
model = SimpleModel()

# Create the layer name to extract features from
layer_name = "fc1"

# Create an output embedding tensor to store the hook output
output_embedding = torch.zeros(2, 3)

ARGS = {
    "model": model,
    "layer_name": layer_name,
    "output_embedding": output_embedding
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_one_audio Ran
ran on a synthesized input
vivoutlaw/tcbp/video_ordering_dataset/Audio_Visual_Place_Temporal.py
code served (permissive licence) · get_code("e3388c4048e39dbf")
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 float, shape (1, 11025, 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 torch
import numpy as np
from scipy.io import wavfile
import tempfile
import os

torch.manual_seed(0)

# Create a temporary WAV file with int16 audio data
temp_dir = tempfile.mkdtemp()
temp_audio_file = os.path.join(temp_dir, "test_audio.wav")

# Generate a simple int16 audio signal at 16000 Hz
sample_rate = 16000
duration_sec = 0.5
num_samples = int(sample_rate * duration_sec)
audio_data = np.random.randint(-32768, 32767, num_samples, dtype=np.int16)

# Write the WAV file
wavfile.write(temp_audio_file, sample_rate, audio_data)

ARGS = {
    "audio_filename": temp_audio_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, 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 float, shape (1, 11025, 1) — shape (1, 11025, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

True understanding of videos comes from a joint analysis of all its modalities: the video frames, the audio track, and any accompanying text such as closed captions. We present a way to learn a compact multimodal feature representation that encodes all these modalities. Our model parameters are learned through a proxy task of inferring the temporal ordering of a set of unordered videos in a timeline. To this end, we create a new multimodal dataset for temporal ordering that consists of approximately 30K scenes (2-6 clips per scene) based on the "Large Scale Movie Description Challenge". We analyze and evaluate the individual and joint modalities on three challenging tasks: (i) inferring the temporal ordering of a set of videos; and (ii) action recognition. We demonstrate empirically that multimodal representations are indeed complementary, and can play a key role in improving the performance of many applications.

For agents

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

get_harvested_code_for_paper("2004.02205")
get_code_for_paper("2004.02205")
have("2004.02205")

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

curl https://syntology.ai/api/ran/2004.02205.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.02205.svg)](https://syntology.ai/paper/2004.02205)

Connect an agent — have() is free.