{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/weakly-supervised-action-segmentation-using","title":"Fast Weakly Supervised Action Segmentation Using Mutual Consistency","arxiv_id":"1904.03116","date":"2019-04-05","proceeding":null,"authors":["Yaser Souri","Mohsen Fayyaz","Luca Minciullo","Gianpiero Francesca","Juergen Gall"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1904.03116v4","url_pdf":"https://arxiv.org/pdf/1904.03116v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"weakly-supervised-action-segmentation-using","repo_url":"https://github.com/yassersouri/MuCon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"weakly-supervised-action-segmentation","task_name":"Weakly Supervised Action Segmentation (Transcript)"}],"methods":[{"method_slug":"1d-cnn","method_name":"1D CNN"},{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"MuCon","rank_in_archive_order":24,"of":37,"metrics":{"Acc":"62.8","Average F1":"62.6","Edit":"76.3","F1@10%":"73.2","F1@25%":"66.1","F1@50%":"48.4"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-segmentation","task":"Weakly Supervised Action Segmentation (Transcript)","dataset":"Breakfast","model":"MuCon","rank_in_archive_order":5,"of":7,"metrics":{"Acc":"48.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03116","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}