Papers › Long Movie Clip Classification with State-Space Video Models

Long Movie Clip Classification with State-Space Video Models

4 Apr 2022arXiv:2204.01692archive 2025-07-28

Md Mohaiminul Islam, Gedas Bertasius

Most modern video recognition models are designed to operate on short video clips (e.g., 5-10s in length). Thus, it is challenging to apply such models to long movie understanding tasks, which typically require sophisticated long-range temporal reasoning. The recently introduced video transformers partially address this issue by using long-range temporal self-attention. However, due to the quadratic cost of self-attention, such models are often costly and impractical to use. Instead, we propose ViS4mer, an efficient long-range video model that combines the strengths of self-attention and the recently introduced structured state-space sequence (S4) layer. Our model uses a standard Transformer encoder for short-range spatiotemporal feature extraction, and a multi-scale temporal S4 decoder for subsequent long-range temporal reasoning. By progressively reducing the spatiotemporal feature resolution and channel dimension at each decoder layer, ViS4mer learns complex long-range spatiotemporal dependencies in a video. Furthermore, ViS4mer is 2.63× faster and requires 8× less GPU memory than the corresponding pure self-attention-based model. Additionally, ViS4mer achieves state-of-the-art results in 6 out of 9 long-form movie video classification tasks on the Long Video Understanding (LVU) benchmark. Furthermore, we show that our approach successfully generalizes to other domains, achieving competitive results on the Breakfast and the COIN procedural activity datasets. The code is publicly available at: https://github.com/md-mohaiminul/ViS4mer.

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 18 code samples: 16 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 18: 11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 7 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: 16 samples from 1 repository, 9 ran (3 with no instrument failure; 6 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 11 samples that ran has no recorded date.

md-mohaiminul/ViS4mer officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 9 ran (6 instrument-failed) · 7 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

18 samples harvested: 11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 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
7ran · our draft was wrong
1ran; the contract check could not run
2ran
7unverified

Licence: 2 of the 18 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 md-mohaiminul/ViS4mer. 2 samples are listed last, in a group without a repository. “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.

md-mohaiminul/ViS4mer official repository 16 samples, 9 ran (6 instrument-failed) · 7 unverified
LinearActivation in 16 papers models.py ran · our draft was wrong MIT (permissive) · 8538f8c63d35c959 · report fixture: signature d_input:int/0/int, d_output:int/0/int, bias:bool/0/bool, zero_bias_init:bool/0/bool, transposed:bool/0/bool, initializer:str/0/str, activation:str/0/str, activate:bool/0/bool, weight_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22
SSKernelSlow models.py ran · metamorphic tier: deterministic MIT (permissive) · 39159b1078607edf · report fixture: returned SSKernelSlow · level recorded 2026-09-22
TransposedLinear models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 71048363ae476934 · report fixture: returned TransposedLinear · level recorded 2026-09-22
get_logger in 383 papers models.py ran · our draft was wrong MIT (permissive) · 61139ec62260b411 · report fixture: signature name:str/0/str, level:int/0/int · returned Logger · level recorded 2026-09-22
krylov models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 030ade7f4f951898 · report fixture: signature L:int/0/int, A:Tensor/3/float, b:Tensor/2/float, c:Tensor/2/float, return_power:bool/0/bool · returned Tensor · level recorded 2026-09-22
nplr in 6 papers models.py ran · our draft was wrong MIT (permissive) · 52f5a73f3505ecee · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/? · returned tuple · level recorded 2026-09-22
power in 16 papers models.py ran · our draft was wrong fingerprinted MIT (permissive) · fae8dcc7964cac77 · report fixture: signature L:int/0/int, A:Tensor/2/float, v:Tensor/2/float · returned tuple · level recorded 2026-09-22
rank_correction in 7 papers models.py ran · honoured contract MIT (permissive) · 3dce80b93036d192 · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
transition in 16 papers models.py ran · our draft was wrong MIT (permissive) · 87ea80b70e1e70b9 · report fixture: signature measure:str/0/str, N:int/0/int, beta:float/0/float, alpha:float/0/float · returned tuple · level recorded 2026-09-22
HippoSSKernel models.py unverified MIT (permissive) · 717d9447a001c75e · report
OptimModule in 5 papers models.py unverified MIT (permissive) · 8076f48bc17f0bc5 · report
S4 models.py unverified MIT (permissive) · 0bbcf5a8797deb01 · report
SSKernelNPLR models.py unverified MIT (permissive) · a0cd8021dee737f7 · report
ViS4mer models.py unverified MIT (permissive) · b7f3ea1de74c55c3 · report
_broadcast_dims models.py unverified MIT (permissive) · 0c3303405c8151e9 · report
cauchy_conj models.py unverified MIT (permissive) · fba66bbdebdb89e4 · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
Activation in 28 papers repository not located ran · our draft was wrong licence of this copy not recorded · 89b10a8b26bbb7ed · report fixture: signature activation:str/0/str, dim:int/0/int · returned ReLU · level recorded, date not recorded
get_initializer in 32 papers repository not located ran · our draft was wrong licence of this copy not recorded · 49d9214ec79a8edb · report fixture: signature name:str/0/str, activation:str/0/str · returned partial · level recorded 2026-09-22

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 ViS4mer (graph method: ViS4mer). 18 bricks; individually on a fixture: 11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. ViS4mer entry · level 0 · unverified · b7f3ea1de74c55c3
  2. S4 model · level 0 · unverified · 0bbcf5a8797deb01
  3. Activation helper · level 1 · ran · our draft was wrong · 89b10a8b26bbb7ed
  4. HippoSSKernel helper · level 0 · unverified · 717d9447a001c75e
  5. LinearActivation helper · level 1 · ran · our draft was wrong · 8538f8c63d35c959
  6. SSKernelNPLR model · level 0 · unverified · a0cd8021dee737f7
  7. SSKernelSlow helper · level 1 · ran · 39159b1078607edf
  8. nplr helper · level 1 · ran · our draft was wrong · 52f5a73f3505ecee
  9. power helper · level 1 · ran · our draft was wrong · fae8dcc7964cac77
  10. transition helper · level 1 · ran · our draft was wrong · 87ea80b70e1e70b9
  11. TransposedLinear helper · level 1 · ran · 71048363ae476934
  12. get_initializer helper · level 1 · ran · our draft was wrong · 49d9214ec79a8edb
  13. OptimModule helper · level 0 · unverified · 8076f48bc17f0bc5
  14. cauchy_conj helper · level 0 · unverified · fba66bbdebdb89e4
  15. krylov helper · level 1 · ran; the contract check could not run (RAISES) · 030ade7f4f951898
  16. rank_correction helper · level 1 · ran · honoured contract · 3dce80b93036d192
  17. _broadcast_dims helper · level 0 · unverified · 0c3303405c8151e9
  18. get_logger helper · level 1 · ran · our draft was wrong · 61139ec62260b411

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="2204.01692") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClassificationDecoderVideo ClassificationVideo RecognitionVideo Understanding

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Classification Breakfast ViS4mer Accuracy (%) 88.2 #6 of 9 Archive leaderboard report
Video Classification COIN ViS4mer Accuracy (%) 88.4 #6 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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