SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.03457 · 2020

VideoMix: Rethinking Data Augmentation for Video Classification

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures of our instrument; 1 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/2012.03457.json · badge: /api/ran/2012.03457.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
jayChung0302/videomix reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
speed_jitter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jayChung0302/videomix/videomix.py
code served (permissive licence) · get_code("574c25015a59f422")
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 Tensor, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 numpy as np
import random

torch.manual_seed(0)
np.random.seed(0)
random.seed(0)

# The function expects:
# - frames: a tensor of shape (batch_size, channels, time, height, width)
# - alpha: float for beta distribution
# - speed_mode: either 'variation' or an integer string/int
# - mode: 'rgb' or something else (affects channel count)
# - max_speed: int for max speed value
# - prob: float for probability (not actually used in function body)

# Create a minimal frames tensor
# Shape: (batch_size=2, channels=3, time=64, height=224, width=224)
# The function accesses frames with indices up to around key_idx + 2*speed + 2
# With time=64, this should be safe for reasonable speed values
frames = torch.randn(2, 3, 64, 224, 224)

ARGS = {
    'frames': frames,
    'alpha': 0.5,
    'speed_mode': 'variation',
    'mode': 'rgb',
    'max_speed': 2,
    'prob': 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
stackmix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jayChung0302/videomix/videomix.py
code served (permissive licence) · get_code("8b167e7cc22f09f0")
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 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 torch
import numpy as np
import random

torch.manual_seed(0)
np.random.seed(0)
random.seed(0)

# x: 5D tensor (batch_size, channels, nframes, height, width)
# y: 3D tensor (batch_size, num_classes, nframes)
# alpha: float for beta distribution
# prob: float probability threshold
# nframes: int number of frames

batch_size = 2
channels = 3
nframes = 64
height = 4
width = 5
num_classes = 10

x = torch.randn(batch_size, channels, nframes, height, width)
y = torch.randn(batch_size, num_classes, nframes)
alpha = 1.5
prob = 0.8

ARGS = {
    'x': x,
    'y': y,
    'alpha': alpha,
    'prob': prob,
    'nframes': nframes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
tubemix Not yet run
unverified (harvested, no recorded run)
jayChung0302/videomix/videomix.py
code served (permissive licence) · get_code("c488b01d4015cb6d")
How it ran

no invocation recorded.

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

State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content, leading to sub-optimal generalization performances. Recent data augmentation strategies have been reported to address the overfitting problems in static image classifiers. Despite the effectiveness on the static image classifiers, data augmentation has rarely been studied for videos. For the first time in the field, we systematically analyze the efficacy of various data augmentation strategies on the video classification task. We then propose a powerful augmentation strategy VideoMix. VideoMix creates a new training video by inserting a video cuboid into another video. The ground truth labels are mixed proportionally to the number of voxels from each video. We show that VideoMix lets a model learn beyond the object and scene biases and extract more robust cues for action recognition. VideoMix consistently outperforms other augmentation baselines on Kinetics and the challenging Something-Something-V2 benchmarks. It also improves the weakly-supervised action localization performance on THUMOS'14. VideoMix pretrained models exhibit improved accuracies on the video detection task (AVA).

For agents

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

get_harvested_code_for_paper("2012.03457")
get_code_for_paper("2012.03457")
have("2012.03457")

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

curl https://syntology.ai/api/ran/2012.03457.json

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

[![Syntology run record](https://syntology.ai/api/ran/2012.03457.svg)](https://syntology.ai/paper/2012.03457)

Connect an agent — have() is free.