{"id":33018,"date":"2026-01-21T17:03:05","date_gmt":"2026-01-21T17:03:05","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/fast-weakly-supervised-action-segmentation-using-mutual-consistency\/"},"modified":"2026-09-17T11:27:17","modified_gmt":"2026-09-17T11:27:17","slug":"fast-weakly-supervised-action-segmentation-using-mutual-consistency","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/fast-weakly-supervised-action-segmentation-using-mutual-consistency\/","title":{"rendered":"Fast Weakly Supervised Action Segmentation Using Mutual Consistency"},"content":{"rendered":"<p>Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from transcripts are appealing. In this paper, we propose a novel end-to-end approach for weakly supervised action segmentation based on a two-branch neural network. The two branches of our network predict two redundant but different representations for action segmentation and we propose a novel mutual consistency (MuCon) loss that enforces the consistency of the two redundant representations. Using the MuCon loss together with a loss for transcript prediction, our proposed approach achieves the accuracy of state-of-the-art approaches while being 14 times faster to train and 20 times faster during inference. The MuCon loss proves beneficial even in the fully supervised setting.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from transcripts are appealing. In this paper, we propose a novel end-to-end approach for weakly supervised action segmentation based on a two-branch neural network. The two branches of our network predict two redundant but different representations [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-33018","publication","type-publication","status-publish","hentry","publication-type-article"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/33018","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/33018\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=33018"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=33018"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}