</> Code with Papers by Syntology

Papers › Unsupervised learning of action classes with continuous temporal embedding

Unsupervised learning of action classes with continuous temporal embedding

8 Apr 2019CVPR 2019 6arXiv:1904.04189archive 2025-07-28

Anna Kukleva, Hilde Kuehne, Fadime Sener, Juergen Gall

The task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently. One problem in this context arises from the need to define and label action boundaries to create annotations for training which is very time and cost intensive. To address this issue, we propose an unsupervised approach for learning action classes from untrimmed video sequences. To this end, we use a continuous temporal embedding of framewise features to benefit from the sequential nature of activities. Based on the latent space created by the embedding, we identify clusters of temporal segments across all videos that correspond to semantic meaningful action classes. The approach is evaluated on three challenging datasets, namely the Breakfast dataset, YouTube Instructions, and the 50Salads dataset. While previous works assumed that the videos contain the same high level activity, we furthermore show that the proposed approach can also be applied to a more general setting where the content of the videos is unknown.

PaperPDFConference PDFCode

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

Code

annusha/unsup_temp_embed officialmentioned in papermentioned on GitHubpytorchMIT report
frans-db/progress-prediction mentioned 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 SegmentationUnsupervised Action Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Action Segmentation Breakfast CTE Acc 41.8 #7 of 8 Archive leaderboard report
Unsupervised Action Segmentation Breakfast CTE F1 26.4 #7 of 8 Archive leaderboard report
Unsupervised Action Segmentation Breakfast CTE JSD 87.4 #7 of 8 Archive leaderboard report
Unsupervised Action Segmentation Breakfast CTE Precision 25.8 #7 of 8 Archive leaderboard report
Unsupervised Action Segmentation Breakfast CTE Recall 27.0 #7 of 8 Archive leaderboard report
Unsupervised Action Segmentation IKEA ASM CTE Accuracy 23.1 #3 of 5 Archive leaderboard report
Unsupervised Action Segmentation IKEA ASM CTE F1 22.6 #3 of 5 Archive leaderboard report
Unsupervised Action Segmentation IKEA ASM CTE JSD 73.7 #3 of 5 Archive leaderboard report
Unsupervised Action Segmentation IKEA ASM CTE Precision 28.1 #3 of 5 Archive leaderboard report
Unsupervised Action Segmentation IKEA ASM CTE Recall 18.9 #3 of 5 Archive leaderboard report
Unsupervised Action Segmentation Youtube INRIA Instructional CTE Acc 39 #8 of 8 Archive leaderboard report
Unsupervised Action Segmentation Youtube INRIA Instructional CTE F1 28.3 #8 of 8 Archive leaderboard report
Unsupervised Action Segmentation Youtube INRIA Instructional CTE Precision 39.3 #8 of 8 Archive leaderboard report
Unsupervised Action Segmentation Youtube INRIA Instructional CTE Recall 22.1 #8 of 8 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