Papers › Action Shuffle Alternating Learning for Unsupervised Action Segmentation

Action Shuffle Alternating Learning for Unsupervised Action Segmentation

5 Apr 2021CVPR 2021 1arXiv:2104.02116archive 2025-07-28

Jun Li, Sinisa Todorovic

This paper addresses unsupervised action segmentation. Prior work captures the frame-level temporal structure of videos by a feature embedding that encodes time locations of frames in the video. We advance prior work with a new self-supervised learning (SSL) of a feature embedding that accounts for both frame- and action-level structure of videos. Our SSL trains an RNN to recognize positive and negative action sequences, and the RNN's hidden layer is taken as our new action-level feature embedding. The positive and negative sequences consist of action segments sampled from videos, where in the former the sampled action segments respect their time ordering in the video, and in the latter they are shuffled. As supervision of actions is not available and our SSL requires access to action segments, we specify an HMM that explicitly models action lengths, and infer a MAP action segmentation with the Viterbi algorithm. The resulting action segmentation is used as pseudo-ground truth for estimating our action-level feature embedding and updating the HMM. We alternate the above steps within the Generalized EM framework, which ensures convergence. Our evaluation on the Breakfast, YouTube Instructions, and 50Salads datasets gives superior results to those of the state of the art.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action SegmentationSegmentationSelf-Supervised LearningUnsupervised Action Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Action Segmentation Breakfast ASAL Acc 52.5 #4 of 8 Archive leaderboard report
Unsupervised Action Segmentation Breakfast ASAL F1 37.9 #4 of 8 Archive leaderboard report
Unsupervised Action Segmentation Youtube INRIA Instructional ASAL Acc 44.9 #6 of 8 Archive leaderboard report
Unsupervised Action Segmentation Youtube INRIA Instructional ASAL F1 32.1 #6 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