Browse State-of-the-Art › Unsupervised Action Segmentation
Unsupervised Action Segmentation
9 papers with code · 4 benchmarks · 4 datasets archive 2025-07-28
Unsupervised Action Segmentation is a challenging problem in high-level video understanding, where the goal is to segment a temporally untrimmed sequence into distinct action segments without access to ground truth labels during training. Unlike supervised methods, which rely on annotated datasets, unsupervised approaches aim to discover the underlying structure of actions directly from data. This makes the task particularly valuable for scenarios with limited labeled data or large-scale unlabeled video datasets. The results of Unsupervised Action Segmentation can be further applied to tasks such as action localization and video summarization.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Breakfast (8 rows) | HVQ | Hierarchical Vector Quantization for Unsupervised Action Segmentation | code | — | Compare |
| Youtube INRIA Instructional (8 rows) | LSTM+AL | A Perceptual Prediction Framework for Self Supervised Event Segmentation | code | Syntology official: harvested, nothing ran · 0 ran · 1 unverified | Compare |
| IKEA ASM (5 rows) | HVQ | Hierarchical Vector Quantization for Unsupervised Action Segmentation | code | — | Compare |
| 50 Salads (3 rows) | LSTM+AL | A Perceptual Prediction Framework for Self Supervised Event Segmentation | code | Syntology official: harvested, nothing ran · 0 ran · 1 unverified | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 16 · with a code link: 9 · where Syntology ran a sample: 2 (1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 16 tagged: 1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 16 of 16, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.
-
8 Apr 2019 2 repositories listedThe task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently.
-
23 Dec 2024 1 repository listedIn this work, we address unsupervised temporal action segmentation, which segments a set of long, untrimmed videos into semantically meaningful segments that are consistent across videos.
-
13 Sep 2024 1 repository listedIn this paper, we address a challenging task, synchronous motion captioning, that aim to generate a language description synchronized with human motion sequences.
-
1 Apr 2024 1 repository listedWe evaluate our segmentation approach and unsupervised learning pipeline on the Breakfast, 50-Salads, YouTube Instructions and Desktop Assembly datasets, yielding state-of-the-art results for the unsupervised video…
-
31 May 2023 1 repository listedThe frame-level prediction module is trained in an unsupervised manner via temporal optimal transport.
-
13 Apr 2023 1 repository listedIn this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data.
-
27 May 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)The temporal optimal transport module enables our approach to learn effective representations for unsupervised activity segmentation.
-
20 Mar 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks.
-
12 Nov 2018 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)We also show that the proposed approach is able to learn highly discriminative features that help improve action recognition when used in a representation learning paradigm.
-
TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering9 Mar 2023 0 repositories listedTemporal action segmentation in untrimmed videos has gained increased attention recently.
-
Fast and Unsupervised Action Boundary Detection for Action Segmentation1 Jan 2022 0 repositories listedTo deal with the great number of untrimmed videos produced every day, we propose an efficient unsupervised action segmentation method by detecting boundaries, named action boundary detection (ABD).
-
Unsupervised Action Segmentation for Instructional Videos7 Jun 2021 0 repositories listedIn this paper we address the problem of automatically discovering atomic actions in unsupervised manner from instructional videos, which are rarely annotated with atomic actions.
-
5 Apr 2021 0 repositories listedThis paper addresses unsupervised action segmentation.
-
Watch-n-Patch: Unsupervised Learning of Actions and Relations11 Mar 2016 0 repositories listedThere is a large variation in the activities that humans perform in their everyday lives.
-
Watch-Bot: Unsupervised Learning for Reminding Humans of Forgotten Actions14 Dec 2015 0 repositories listedWe present a robotic system that watches a human using a Kinect v2 RGB-D sensor, detects what he forgot to do while performing an activity, and if necessary reminds the person using a laser pointer to point out the…
-
1 Jun 2015 0 repositories listedWe focus on modeling human activities comprising multiple actions in a completely unsupervised setting.
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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