Papers › Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

Kronecker Mask and Interpretive Prompts are Language-Action Video Learners

5 Feb 2025arXiv:2502.03549archive 2025-07-28

Jingyi Yang, Zitong Yu, Xiuming Ni, Jia He, Hui Li

Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose CLAVER: a Contrastive Language-Action Video Learner, designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to the alignment of dynamic action behaviors and abstract verbs. Specifically, we introduce a novel Kronecker mask attention for temporal modeling. Our tailored Kronecker mask offers three benefits 1) it expands the temporal receptive field for each token, 2) it serves as an effective spatiotemporal heterogeneity inductive bias, mitigating the issue of spatiotemporal homogenization, and 3) it can be seamlessly plugged into transformer-based models. Regarding the textual branch, we leverage large language models to generate diverse, sentence-level and semantically rich interpretive prompts of actions, which shift the model's focus towards the verb comprehension. Extensive experiments on various benchmarks and learning scenarios demonstrate the superiority and generality of our approach. The code will be available soon.

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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 9 ran (9 with no instrument failure; 0 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.

yjyddq/CLAVER officialmentioned on GitHubpytorchSyntology: 11 samples, 9 ran (0 instrument-failed) · 2 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

11 samples harvested: 9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result. “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.

9ran
2unverified

Licence: 11 of the 11 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 yjyddq/CLAVER. “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 4 samples 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

yjyddq/CLAVER official repository 11 samples, 9 ran (0 instrument-failed) · 2 unverified
CLIP in 25 papers models/claver.py ran no licence file found · pointer only · ea3373815e1a7a63 · report fixture: returned CLIP · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
models/claver.py ran fingerprinted no licence file found · pointer only · 02c3d66d7386b4ce · report fixture: returned DropPath · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/claver.py ran fingerprinted no licence file found · pointer only · 07f83dd5e1159854 · report fixture: returned LayerNorm · level recorded 2026-09-22
ResidualAttentionBlock in 38 papers models/claver.py ran no licence file found · pointer only · 23a40303b56bf120 · report fixture: returned ResidualAttentionBlock · level recorded 2026-09-22
SpatialAttentionBlock models/claver.py ran no licence file found · pointer only · 923f5373bf4e3656 · report fixture: returned SpatialAttentionBlock · level recorded 2026-09-22
SpatialTransformer in 23 papers models/claver.py ran fingerprinted no licence file found · pointer only · 0ed72504b4471f32 · report fixture: returned SpatialTransformer · level recorded 2026-09-22
TemporalAttentionBlock models/claver.py ran no licence file found · pointer only · 404e08757bf09cdc · report fixture: returned TemporalAttentionBlock · level recorded 2026-09-22
TemporalTransformer models/claver.py ran no licence file found · pointer only · 1df85a83617ec2e9 · report fixture: returned TemporalTransformer · level recorded 2026-09-22
Transformer in 173 papers models/claver.py ran fingerprinted no licence file found · pointer only · 54f791f044d7891c · report fixture: returned Transformer · level recorded 2026-09-22
CLAVER models/claver.py unverified no licence file found · pointer only · ecee626d87b97fac · report
VideoVisionTransformer models/claver.py unverified no licence file found · pointer only · 33ddf59a02be66bf · 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 CLAVER (graph method: CLAVER). 13 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. CLAVER entry · level 0 · unverified · ecee626d87b97fac
  2. CLIP helper · level 1 · ran · ea3373815e1a7a63
  3. LayerNorm helper · level 1 · ran · 07f83dd5e1159854
  4. Transformer helper · level 1 · ran · 54f791f044d7891c
  5. VideoVisionTransformer model · level 0 · unverified · 33ddf59a02be66bf
  6. ResidualAttentionBlock helper · level 1 · ran · 23a40303b56bf120
  7. SpatialTransformer helper · level 1 · ran · 0ed72504b4471f32
  8. TemporalTransformer helper · level 1 · ran · 1df85a83617ec2e9
  9. QuickGELU helper · level 1 · ran · 8c5c4de012c0aab9
  10. SpatialAttentionBlock helper · level 1 · ran · 923f5373bf4e3656
  11. TemporalAttentionBlock helper · level 1 · ran · 404e08757bf09cdc
  12. DropPath helper · level 1 · ran · 02c3d66d7386b4ce
  13. drop_path helper · level 1 · ran; the contract check could not run · 3ac6b7d76e8e3584

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="2502.03549") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action RecognitionInductive Bias

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionCLIPFocusSoftmax

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