SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.00869 · 2019

More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 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 1 has no contract verdict; 0 failures of our instrument; 5 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/1912.00869.json · badge: /api/ran/1912.00869.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
IBM/bLVNet-TAM canonical (classifier label)
classifier basis: census
1 ran · 5 no recorded run
FunctionStatusWhere it lives
get_frame_list Ran
ran on a synthesized input
IBM/bLVNet-TAM/core/models/blvnet_tam_backbone.py
code served (permissive licence) · get_code("3f3f0085bff43541")
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 1, 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 itertools

torch.manual_seed(0)

# Analyzing the function:
# - init_list: a list that gets iterated over and elements are added to
# - num_frames: an integer used in multiplication
# - batch_size: an integer used in range()
# The function creates a list of frame indices by offsetting init_list by multiples of num_frames

ARGS = {
    "init_list": [0, 1, 2],
    "num_frames": 10,
    "batch_size": 3
}
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 list, ndim 1, 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
accuracy Not yet run
unverified (harvested, no recorded run)
IBM/bLVNet-TAM/core/video_utils.py
code served (permissive licence) · get_code("f9d7c39899b76464")
How it ran

no invocation recorded.

blvnet_tam_backbone Not yet run
unverified (harvested, no recorded run)
IBM/bLVNet-TAM/core/models/blvnet_tam_backbone.py
code served (permissive licence) · get_code("88e0b6615c11d561")
How it ran

no invocation recorded.

build_model Not yet run
unverified (harvested, no recorded run)
IBM/bLVNet-TAM/core/video_utils.py
code served (permissive licence) · get_code("48d6462978ea5c3b")
How it ran

no invocation recorded.

get_augmentor Not yet run
unverified (harvested, no recorded run)
IBM/bLVNet-TAM/core/video_utils.py
code served (permissive licence) · get_code("ad3e2f9e9ecf926f")
How it ran

no invocation recorded.

random_clip Not yet run
unverified (harvested, no recorded run)
IBM/bLVNet-TAM/core/video_dataset.py
code served (permissive licence) · get_code("7edc2bcdea46f6ba")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a lightweight and memory-friendly architecture for action recognition that performs on par with or better than current architectures by using only a fraction of resources. The proposed architecture is based on a combination of a deep subnet operating on low-resolution frames with a compact subnet operating on high-resolution frames, allowing for high efficiency and accuracy at the same time. We demonstrate that our approach achieves a reduction by $3\sim4$ times in FLOPs and $\sim2$ times in memory usage compared to the baseline. This enables training deeper models with more input frames under the same computational budget. To further obviate the need for large-scale 3D convolutions, a temporal aggregation module is proposed to model temporal dependencies in a video at very small additional computational costs. Our models achieve strong performance on several action recognition benchmarks including Kinetics, Something-Something and Moments-in-time. The code and models are available at https://github.com/IBM/bLVNet-TAM.

For agents

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

get_harvested_code_for_paper("1912.00869")
get_code_for_paper("1912.00869")
have("1912.00869")

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

curl https://syntology.ai/api/ran/1912.00869.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.00869.svg)](https://syntology.ai/paper/1912.00869)

Connect an agent — have() is free.