Papers › Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to...

Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation

1 Sep 2022arXiv:2209.00638archive 2025-07-28

Nadine Behrmann, S. Alireza Golestaneh, Zico Kolter, Juergen Gall, Mehdi Noroozi

This paper introduces a unified framework for video action segmentation via sequence to sequence (seq2seq) translation in a fully and timestamp supervised setup. In contrast to current state-of-the-art frame-level prediction methods, we view action segmentation as a seq2seq translation task, i.e., mapping a sequence of video frames to a sequence of action segments. Our proposed method involves a series of modifications and auxiliary loss functions on the standard Transformer seq2seq translation model to cope with long input sequences opposed to short output sequences and relatively few videos. We incorporate an auxiliary supervision signal for the encoder via a frame-wise loss and propose a separate alignment decoder for an implicit duration prediction. Finally, we extend our framework to the timestamp supervised setting via our proposed constrained k-medoids algorithm to generate pseudo-segmentations. Our proposed framework performs consistently on both fully and timestamp supervised settings, outperforming or competing state-of-the-art on several datasets. Our code is publicly available at https://github.com/boschresearch/UVAST.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2209.00638")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

boschresearch/uvast officialmentioned in papermentioned on GitHubpytorch 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

2 samples harvested; 2 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran

Licence: 2 of the 2 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 boschresearch/uvast. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

TransformerDecoder_UVAST boschresearch/uvast/uvast_dec.py official repository ran fingerprinted AGPL-3.0 (copyleft) · pointer only · 53957dadad8b98a6 · report
_get_clones boschresearch/uvast/uvast_dec.py official repository ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · 5c98e971f97efda9 · report

Tasks

Action SegmentationDecoderTemporal Action SegmentationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation 50 Salads UVAST Acc 87.4 #7 of 28 Archive leaderboard report
Action Segmentation 50 Salads UVAST Edit 83.9 #7 of 28 Archive leaderboard report
Action Segmentation 50 Salads UVAST F1@10% 89.1 #7 of 28 Archive leaderboard report
Action Segmentation 50 Salads UVAST F1@25% 87.6 #7 of 28 Archive leaderboard report
Action Segmentation 50 Salads UVAST F1@50% 81.7 #7 of 28 Archive leaderboard report
Action Segmentation Assembly101 UVAST Edit 31.5 #5 of 7 Archive leaderboard report
Action Segmentation Assembly101 UVAST F1@10% 32.1 #5 of 7 Archive leaderboard report
Action Segmentation Assembly101 UVAST F1@25% 28.3 #5 of 7 Archive leaderboard report
Action Segmentation Assembly101 UVAST F1@50% 20.8 #5 of 7 Archive leaderboard report
Action Segmentation Assembly101 UVAST MoF 37.4 #5 of 7 Archive leaderboard report
Action Segmentation Breakfast UVAST Acc 69.7 #12 of 37 Archive leaderboard report
Action Segmentation Breakfast UVAST Average F1 68.8 #12 of 37 Archive leaderboard report
Action Segmentation Breakfast UVAST Edit 77.1 #12 of 37 Archive leaderboard report
Action Segmentation Breakfast UVAST F1@10% 76.9 #12 of 37 Archive leaderboard report
Action Segmentation Breakfast UVAST F1@25% 71.5 #12 of 37 Archive leaderboard report
Action Segmentation Breakfast UVAST F1@50% 58 #12 of 37 Archive leaderboard report
Action Segmentation GTEA UVAST Acc 80.2 #10 of 28 Archive leaderboard report
Action Segmentation GTEA UVAST Edit 92.1 #10 of 28 Archive leaderboard report
Action Segmentation GTEA UVAST F1@10% 92.7 #10 of 28 Archive leaderboard report
Action Segmentation GTEA UVAST F1@25% 91.3 #10 of 28 Archive leaderboard report
Action Segmentation GTEA UVAST F1@50% 81 #10 of 28 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 ConnectionsDropoutLSTMLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh ActivationTransformer

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