SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.04287 · CVPR · 2022

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

Zhirong Wu, Stephen Lin, Fangyun Wei, Yutong Chen, Xiao Sun

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure 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/2203.04287.json · badge: /api/ran/2203.04287.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
rzhao-zhsq/cv-slt community
Papers with Code archive
5 ran · 4 no recorded run
edwardguil/MMTL community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
BaseGlossTokenizer Ran
ran on a synthesized input · constructed an object; no result was computed
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("628d2279ee01c307")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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. A run is recorded.

BaseTokenizer Ran
ran on a synthesized input · constructed an object; no result was computed
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("7ac67b2d12d208fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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. A run is recorded.

GlossTokenizer_G2T Ran
ran on a synthesized input · constructed an object; no result was computed
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("52d19c31280e6175")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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. A run is recorded.

XentLoss Ran
ran on a synthesized input · constructed an object; no result was computed
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("72193bb924fb9f48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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. A run is recorded.

shift_tokens_right Ran
ran; our contract draft was wrong, not the code
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("7de42cc5069555cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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. A run is recorded.

TextTokenizer Not yet run
unverified (harvested, no recorded run)
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("0ad00be0e2fc2720")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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.

TranslationNetwork Not yet run
unverified (harvested, no recorded run)
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("a37b24d391d298d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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.

freeze_params Not yet run
unverified (harvested, no recorded run)
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("63b27b7140c6bf81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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.

get_logger Not yet run
unverified (harvested, no recorded run)
rzhao-zhsq/cv-slt/modelling/translation.py
pointer only (licence: NONE) · get_code("cd6cc8d642098d59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rzhao-zhsq/cv-slt 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.

load_weights Not yet run
unverified (harvested, no recorded run)
edwardguil/MMTL/s3d.py
code served (permissive licence) · get_code("7d93162312ea626f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 9 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
shift_tokens_right
brick of this paper's assembly: helper
1 other paper
1 later
2023.findings-emnlp.198 (2023 (year only))
Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Method

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

This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pairs of sign videos, gloss annotations and texts, which are an order of magnitude smaller than typical parallel data for training spoken language translation models. Data is thus a bottleneck for training effective sign language translation models. To mitigate this problem, we propose to progressively pretrain the model from generaldomain datasets that include a large amount of external supervision to within-domain datasets. Concretely, we pretrain the sign-to-gloss visual network on the general domain of human actions and the within-domain of a sign-to-gloss dataset, and pretrain the gloss-to-text translation network on the general domain of a multilingual corpus and the within-domain of a gloss-to-text corpus. The joint model is fine-tuned with an additional module named the visuallanguage mapper that connects the two networks. This simple baseline surpasses the previous state-of-the-art results on two sign language translation benchmarks, demonstrating the effectiveness of transfer learning. With its simplicity and strong performance, this approach can serve as a solid baseline for future research.

For agents

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

get_harvested_code_for_paper("2203.04287")
get_code_for_paper("2203.04287")
have("2203.04287")

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

curl https://syntology.ai/api/ran/2203.04287.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.04287.svg)](https://syntology.ai/paper/2203.04287)

Connect an agent — have() is free.