Papers › Uni-Sign: Toward Unified Sign Language Understanding at Scale

Uni-Sign: Toward Unified Sign Language Understanding at Scale

25 Jan 2025arXiv:2501.15187archive 2025-07-28

Zecheng Li, Wengang Zhou, Weichao Zhao, Kepeng Wu, Hezhen Hu, Houqiang Li

Sign language pre-training has gained increasing attention for its ability to enhance performance across various sign language understanding (SLU) tasks. However, existing methods often suffer from a gap between pre-training and fine-tuning, leading to suboptimal results. To address this, we propose Uni-Sign, a unified pre-training framework that eliminates the gap between pre-training and downstream SLU tasks through a large-scale generative pre-training strategy and a novel fine-tuning paradigm. First, we introduce CSL-News, a large-scale Chinese Sign Language (CSL) dataset containing 1,985 hours of video paired with textual annotations, which enables effective large-scale pre-training. Second, Uni-Sign unifies SLU tasks by treating downstream tasks as a single sign language translation (SLT) task during fine-tuning, ensuring seamless knowledge transfer between pre-training and fine-tuning. Furthermore, we incorporate a prior-guided fusion (PGF) module and a score-aware sampling strategy to efficiently fuse pose and RGB information, addressing keypoint inaccuracies and improving computational efficiency. Extensive experiments across multiple SLU benchmarks demonstrate that Uni-Sign achieves state-of-the-art performance across multiple downstream SLU tasks. Dataset and code are available at github.com/ZechengLi19/Uni-Sign.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 14 samples that ran has no recorded date.

zechengli19/uni-sign officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 14 ran (4 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
8ran
1unverified

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zechengli19/uni-sign. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zechengli19/uni-sign official repository 15 samples, 14 ran (4 instrument-failed) · 1 unverified
CPB models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 80cd66c1988913a3 · report fixture: returned CPB · level recorded 2026-09-22
DeformableAttention2D models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7516c3b56850cacc · report fixture: returned DeformableAttention2D · level recorded 2026-09-22
GCN_unit models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0466cd7546eebcf9 · report fixture: returned GCN_unit · level recorded 2026-09-22
Graph in 18 papers models.py ran no licence file found · pointer only · 583daf7eff45fa4a · report fixture: returned Graph · level recorded 2026-09-22
PositionEmbeddingRandom in 8 papers models.py ran · metamorphic tier: deterministic no licence file found · pointer only · b4b3b7f27bbaf3d7 · report fixture: returned PositionEmbeddingRandom · level recorded 2026-09-22
STGCNChain models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 831f516db7c357c1 · report fixture: returned STGCNChain · level recorded 2026-09-22
STGCN_block models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0b1ad55d00569ecb · report fixture: returned STGCN_block · level recorded 2026-09-22
Scale in 8 papers models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 7794c2c5eccf86c7 · report fixture: returned Scale · level recorded 2026-09-22
get_hop_distance in 9 papers models.py ran · our draft was wrong no licence file found · pointer only · c257ac36cba643a2 · report fixture: signature num_node:int/0/int, edge:list/1/list, max_hop:int/0/int · returned ndarray · level recorded 2026-09-22
get_sinusoid_encoding_table in 51 papers models.py ran · honoured contract fingerprinted no licence file found · pointer only · 672ebe50dee3907a · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22
get_stgcn_chain models.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · a268c680f8a1a0a9 · report fixture: signature in_dim:int/0/int, level:str/0/str, kernel_size:tuple/1/int, A:Tensor/3/float, adaptive:bool/0/bool · returned tuple · level recorded 2026-09-22
normalize_digraph in 13 papers models.py ran · violated contract fingerprinted no licence file found · pointer only · 8158f4435afa26b7 · report fixture: signature A:ndarray/2/float · returned ndarray · level recorded 2026-09-22
process_frame in 6 papers demo/online_inference.py ran · our draft was wrong no licence file found · pointer only · 35966f0ff0c5376f · report fixture: signature frame:ndarray/3/int, wholebody:callable/0/? · returned tuple · level recorded, date not recorded
reshape_grid_1d models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a0a1f34a1ba7a55d · report fixture: signature grid:Tensor/3/float, dim:int/0/int, out_dim:int/0/int · returned Tensor · level recorded 2026-09-22
Uni_Sign models.py unverified no licence file found · pointer only · 87156eee5e175aab · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Uni-Sign (graph method: Uni-Sign). 19 bricks; individually on a fixture: 18 ran (of which 8 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 4 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. Uni_Sign entry · level 0 · unverified · 87156eee5e175aab
  2. DeformableAttention2D model · level 1 · ran · 7516c3b56850cacc
  3. Graph helper · level 1 · ran · 583daf7eff45fa4a
  4. get_stgcn_chain helper · level 1 · ran; the contract check could not run (RAISES) · a268c680f8a1a0a9
  5. trunc_normal_ helper · level 1 · ran; the contract check could not run · 02566da69866c48c
  6. CPB helper · level 1 · ran · 80cd66c1988913a3
  7. PositionEmbeddingRandom helper · level 1 · ran · b4b3b7f27bbaf3d7
  8. Scale helper · level 1 · ran · 7794c2c5eccf86c7
  9. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  10. divisible_by helper · level 2 · ran · violated contract · 856d86b39c6005b4
  11. get_sinusoid_encoding_table helper · level 1 · ran · honoured contract · 672ebe50dee3907a
  12. reshape_grid_1d helper · level 1 · ran · our draft was wrong · a0a1f34a1ba7a55d
  13. get_hop_distance helper · level 1 · ran · our draft was wrong · c257ac36cba643a2
  14. normalize_digraph helper · level 1 · ran · violated contract · 8158f4435afa26b7
  15. STGCNChain helper · level 1 · ran · 831f516db7c357c1
  16. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · fa2dd3be10cf9804
  17. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  18. STGCN_block model · level 1 · ran · 0b1ad55d00569ecb
  19. GCN_unit helper · level 1 · ran · 0466cd7546eebcf9

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2501.15187") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Computational EfficiencyGloss-free Sign Language TranslationSign Language RecognitionSign Language TranslationTransfer Learning

Datasets

Introduced by this paper, per the archive.

CSL-News

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sign Language Recognition CSL-Daily Uni-Sign Word Error Rate (WER) 26.0 #4 of 14 Archive leaderboard report
Sign Language Recognition MSASL-1000 Uni-Sign P-C Top-1 Accuracy 76.97 #1 of 2 Archive leaderboard report
Sign Language Recognition MSASL-1000 Uni-Sign P-I Top-1 Accuracy 78.16 #1 of 2 Archive leaderboard report
Sign Language Recognition WLASL-2000 Uni-Sign Top-1 Accuracy 63.52 #2 of 9 Archive leaderboard report
Sign Language Recognition WLASL100 Uni-Sign Official Test Split true #1 of 7 Archive leaderboard report
Sign Language Recognition WLASL100 Uni-Sign Top-1 Accuracy 92.25 #1 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections