Papers › How Much Temporal Long-Term Context is Needed for Action Segmentation?

How Much Temporal Long-Term Context is Needed for Action Segmentation?

22 Aug 2023ICCV 2023 1arXiv:2308.11358archive 2025-07-28

Emad Bahrami, Gianpiero Francesca, Juergen Gall

Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal performance. While transformers can model the long-term context of a video, this becomes computationally prohibitive for long videos. Recent works on temporal action segmentation thus combine temporal convolutional networks with self-attentions that are computed only for a local temporal window. While these approaches show good results, their performance is limited by their inability to capture the full context of a video. In this work, we try to answer how much long-term temporal context is required for temporal action segmentation by introducing a transformer-based model that leverages sparse attention to capture the full context of a video. We compare our model with the current state of the art on three datasets for temporal action segmentation, namely 50Salads, Breakfast, and Assembly101. Our experiments show that modeling the full context of a video is necessary to obtain the best performance for temporal action segmentation.

PaperPDFConference PDFCodeCode Syntology ran

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 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 6 samples from 1 repository, 6 ran (6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ltcontext/ltcontext officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 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.

6ran

Licence: 6 of the 6 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 ltcontext/ltcontext. “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”. “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.

ltcontext/ltcontext official repository 6 samples, 6 ran (0 instrument-failed) · 0 unverified
construct_optimizer in 16 papers ltc/model/optimizer.py ran licence not identified · pointer only · a3c5c349ae92e32c · report fixture: signature model:callable/0/?, cfg:dict/0/? · returned Adam · level recorded 2026-09-24
get_epoch_lr ltc/model/optimizer.py ran licence not identified · pointer only · da97b2878d365e41 · report fixture: signature optimizer:SGD/0/? · returned float · level recorded 2026-09-24
get_loss_func in 26 papers ltc/model/loss.py ran licence not identified · pointer only · 2399cfec24000d94 · report fixture: signature cfg:dict/0/? · returned CEplusMSE · level recorded 2026-09-24
patchify in 32 papers
census: 6 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
ltc/model/attention_utils.py ran licence not identified · pointer only · 89736b7f0b2556b1 · report fixture: signature ts:Tensor/3/float, patch_size:int/0/int, stride:int/0/int · returned Tensor · level recorded 2026-09-24
scaled_dot_product_attention in 43 papers ltc/model/attention_utils.py ran licence not identified · pointer only · 286e98f2ad765c4b · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, att_mask:Tensor/3/bool, position_bias:Tensor/3/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-24
scaled_query_key_mult ltc/model/attention_utils.py ran licence not identified · pointer only · 1da4800fb29c6527 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, att_mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24

Tasks

Action SegmentationSegmentationTemporal Action Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation 50 Salads LTContext Acc 87.7 #6 of 28 Archive leaderboard report
Action Segmentation 50 Salads LTContext Edit 83.2 #6 of 28 Archive leaderboard report
Action Segmentation 50 Salads LTContext F1@10% 89.4 #6 of 28 Archive leaderboard report
Action Segmentation 50 Salads LTContext F1@25% 87.7 #6 of 28 Archive leaderboard report
Action Segmentation 50 Salads LTContext F1@50% 82.0 #6 of 28 Archive leaderboard report
Action Segmentation Assembly101 LTContext Edit 30.4 #2 of 7 Archive leaderboard report
Action Segmentation Assembly101 LTContext F1@10% 33.9 #2 of 7 Archive leaderboard report
Action Segmentation Assembly101 LTContext F1@25% 30.0 #2 of 7 Archive leaderboard report
Action Segmentation Assembly101 LTContext F1@50% 22.6 #2 of 7 Archive leaderboard report
Action Segmentation Assembly101 LTContext MoF 41.2 #2 of 7 Archive leaderboard report
Action Segmentation Breakfast LTContext Acc 74.2 #10 of 37 Archive leaderboard report
Action Segmentation Breakfast LTContext Average F1 70.1 #10 of 37 Archive leaderboard report
Action Segmentation Breakfast LTContext Edit 77.0 #10 of 37 Archive leaderboard report
Action Segmentation Breakfast LTContext F1@10% 77.6 #10 of 37 Archive leaderboard report
Action Segmentation Breakfast LTContext F1@25% 72.6 #10 of 37 Archive leaderboard report
Action Segmentation Breakfast LTContext F1@50% 60.1 #10 of 37 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.

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