Papers › Leveraging triplet loss for unsupervised action segmentation

Leveraging triplet loss for unsupervised action segmentation

13 Apr 2023arXiv:2304.06403archive 2025-07-28

E. Bueno-Benito, B. Tura, M. Dimiccoli

In 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. Our method is a deep metric learning approach rooted in a shallow network with a triplet loss operating on similarity distributions and a novel triplet selection strategy that effectively models temporal and semantic priors to discover actions in the new representational space. Under these circumstances, we successfully recover temporal boundaries in the learned action representations with higher quality compared with existing unsupervised approaches. The proposed method is evaluated on two widely used benchmark datasets for the action segmentation task and it achieves competitive performance by applying a generic clustering algorithm on the learned representations.

PaperPDFCode

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

Code

elenabbbuenob/tsa-actionseg 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action SegmentationClusteringMetric LearningSegmentationUnsupervised Action SegmentationVideo Understanding

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation Breakfast TSA (FINCH) Acc 65.1 #34 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (FINCH) mIoU 52.1 #34 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (Kmeans) Acc 63.7 #35 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (Kmeans) F1 58 #35 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (Kmeans) mIoU 53.3 #35 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (Spectral) Acc 63.2 #36 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (Spectral) F1 57.8 #36 of 37 Archive leaderboard report
Action Segmentation Breakfast TSA (Spectral) mIoU 52.7 #36 of 37 Archive leaderboard report
Action Segmentation Youtube INRIA Instructional TSA (FINCH) Acc 62.4 #1 of 2 Archive leaderboard report
Action Segmentation Youtube INRIA Instructional TSA (FINCH) F1 54.7 #1 of 2 Archive leaderboard report
Action Segmentation Youtube INRIA Instructional TSA (Kmeans) Acc 59.7 #2 of 2 Archive leaderboard report
Action Segmentation Youtube INRIA Instructional TSA (Kmeans) F1 55.3 #2 of 2 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

Triplet Loss

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