{"ID":2892223,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15540","arxiv_id":"2507.15540","title":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","abstract":"We study self-supervised procedure learning, which discovers key steps and their order from a set of unlabeled videos. Previous methods typically learn frame-to-frame correspondences between videos before determining key steps and their order. However, their performance often suffers from order variations, background/redundant frames, and repeated actions. To overcome these challenges, we propose a self-supervised framework, which utilizes a fused Gromov-Wasserstein optimal transport with a structural prior for frame-to-frame mapping. However, optimizing only for the above temporal alignment may lead to degenerate solutions, where all frames are mapped to a small cluster in the embedding space and thus every video is assigned to just one key step. To address that issue, we integrate a contrastive regularization, which maps different frames to various points, avoiding trivial solutions. Finally, extensive experiments on egocentric and third-person benchmarks demonstrate our superior performance over prior works, including OPEL which relies on a classical Kantorovich optimal transport with an optimality prior.","short_abstract":"We study self-supervised procedure learning, which discovers key steps and their order from a set of unlabeled videos. Previous methods typically learn frame-to-frame correspondences between videos before determining key steps and their order. However, their performance often suffers from order variations, background/r...","url_abs":"https://arxiv.org/abs/2507.15540","url_pdf":"https://arxiv.org/pdf/2507.15540v2","authors":"[\"Syed Ahmed Mahmood\",\"Ali Shah Ali\",\"Umer Ahmed\",\"Fawad Javed Fateh\",\"M. Zeeshan Zia\",\"Quoc-Huy Tran\"]","published":"2025-07-21T12:09:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}