SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.06231 · NeurIPS · 2023

Learning Human Action Recognition Representations Without Real Humans

Venkatesh Saligrama, Rameswar Panda, Aude Oliva, Rogerio Feris, Hilde Kuehne, Leonid Karlinsky, Donghyun Kim, Samarth Mishra, Howard Zhong, Souyoung Jin

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 1 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/2311.06231.json · badge: /api/ran/2311.06231.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
howardzh01/ppma canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
howardzh01/PPMA canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input · constructed an object; no result was computed
howardzh01/ppma/code/omnivision/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("eecc5dc23f84ce7c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/ppma (NOASSERTION). 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.

PatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
howardzh01/ppma/code/omnivision/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("ee6120b797d547d3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/ppma (NOASSERTION). 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.

PatchEmbedGeneric Ran
ran on a synthesized input · constructed an object; no result was computed
howardzh01/ppma/code/omnivision/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("c85bbc1f8ae5a2df")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/ppma (NOASSERTION). 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.

get_sinusoid_encoding_table Ran
ran, honoured the contract we drafted
howardzh01/ppma/code/omnivision/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("35a743e50e17e66d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/ppma (NOASSERTION). 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.

init_parameters Ran
ran; our contract draft was wrong, not the code
howardzh01/PPMA/code/omnivision/model/model_init_utils.py
pointer only (licence: NOASSERTION) · get_code("de6af75fa2d1e4ad")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/PPMA (NOASSERTION). 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.

layer_decay_param_modifier Ran
ran; our contract draft was wrong, not the code
howardzh01/PPMA/code/omnivision/optim/layer_decay_param_modifier.py
pointer only (licence: NOASSERTION) · get_code("e627ac7e4b6f7972")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/PPMA (NOASSERTION). 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.

make_functional Ran
ran; our contract draft was wrong, not the code
howardzh01/PPMA/code/omnivision/model/model_wrappers.py
pointer only (licence: NOASSERTION) · get_code("b43c65d053fdd761")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/PPMA (NOASSERTION). 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.

VisionTransformer Not yet run
unverified (harvested, no recorded run)
howardzh01/ppma/code/omnivision/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("3e2d901955f04262")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, howardzh01/ppma (NOASSERTION). 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.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
get_sinusoid_encoding_table
brick of this paper's assembly: helper
21 other papers
11 dated earlier, 1 the same month, 9 later · 1 only as an assembly brick
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2208.07049 (2022-08)
Self-Supervised Vision Transformers for Malware Detection
2302.14042 (2023-02)
Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images
and 18 more not named here

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

Pre-training on massive video datasets has become essential to achieve high action recognition performance on smaller downstream datasets. However, most largescale video datasets contain images of people and hence are accompanied with issues related to privacy, ethics, and data protection, often preventing them from being publicly shared for reproducible research. Existing work has attempted to alleviate these problems by blurring faces, downsampling videos, or training on synthetic data. On the other hand, analysis on the transferability of privacypreserving pre-trained models to downstream tasks has been limited. In this work, we study this problem by first asking the question: can we pre-train models for human action recognition with data that does not include real humans? To this end, we present, for the first time, a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model. We then evaluate the transferability of the representation learned on this data to a diverse set of downstream action recognition benchmarks. Furthermore, we propose a novel pre-training strategy, called Privacy-Preserving MAE-Align, to effectively combine synthetic data and human-removed real data. Our approach outperforms previous baselines by up to 5% and closes the performance gap between human and no-human action recognition representations on downstream tasks, for both linear probing and fine-tuning. Our benchmark, code, and models are available at https://github.com/howardzh01/PPMA. 37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks.

For agents

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

get_harvested_code_for_paper("2311.06231")
get_code_for_paper("2311.06231")
have("2311.06231")

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

curl https://syntology.ai/api/ran/2311.06231.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.06231.svg)](https://syntology.ai/paper/2311.06231)

Connect an agent — have() is free.