{"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/hyperbolic-self-paced-learning-for-self","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","arxiv_id":"2303.06242","date":"2023-03-10","proceeding":null,"authors":["Luca Franco","Paolo Mandica","Bharti Munjal","Fabio Galasso"],"abstract":"Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to complex. However its applicability remains unexplored in unsupervised learning, whereby the knowledge of the task matures during training. We propose a novel HYperbolic Self-Paced model (HYSP) for learning skeleton-based action representations. HYSP adopts self-supervision: it uses data augmentations to generate two views of the same sample, and it learns by matching one (named online) to the other (the target). We propose to use hyperbolic uncertainty to determine the algorithmic learning pace, under the assumption that less uncertain samples should be more strongly driving the training, with a larger weight and pace. Hyperbolic uncertainty is a by-product of the adopted hyperbolic neural networks, it matures during training and it comes with no extra cost, compared to the established Euclidean SSL framework counterparts. When tested on three established skeleton-based action recognition datasets, HYSP outperforms the state-of-the-art on PKU-MMD I, as well as on 2 out of 3 downstream tasks on NTU-60 and NTU-120. Additionally, HYSP only uses positive pairs and bypasses therefore the complex and computationally-demanding mining procedures required for the negatives in contrastive techniques. Code is available at https://github.com/paolomandica/HYSP.","url_abs":"https://arxiv.org/abs/2303.06242v1","url_pdf":"https://arxiv.org/pdf/2303.06242v1.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":"hyperbolic-self-paced-learning-for-self","repo_url":"https://github.com/paolomandica/hysp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"unsupervised-skeleton-based-action","task_name":"Unsupervised Skeleton Based Action Recognition"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"3s-HYSP","rank_in_archive_order":65,"of":135,"metrics":{"Accuracy (CS)":"89.1","Accuracy (CV)":"95.2"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"HYSP","rank_in_archive_order":83,"of":135,"metrics":{"Accuracy (CS)":"86.5","Accuracy (CV)":"93.5"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"3s-HYSP","rank_in_archive_order":49,"of":83,"metrics":{"Accuracy (Cross-Setup)":"86.3","Accuracy (Cross-Subject)":"84.5"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"HYSP","rank_in_archive_order":54,"of":83,"metrics":{"Accuracy (Cross-Setup)":"82","Accuracy (Cross-Subject)":"81.4"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-pku-mmd","task":"Skeleton Based Action Recognition","dataset":"PKU-MMD","model":"3s-HYSP","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy (Cross-Subject)":"96.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.06242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06242"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/paolomandica/HYSP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/paolomandica/hysp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":11},"by_repo_kind":{"official":{"samples":13,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8ba7eaf2c8a7739a","entry":"EMA","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ba7eaf2c8a7739a"}},{"code_sha256_prefix":"dd034bb1c67ea073","entry":"Simam_Drop","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd034bb1c67ea073"}},{"code_sha256_prefix":"180f114b9cbc15ea","entry":"DropBlockT_1d","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"180f114b9cbc15ea"}},{"code_sha256_prefix":"bc2bd6c395543b89","entry":"DropBlock_Ske","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc2bd6c395543b89"}},{"code_sha256_prefix":"2bbb5e685ad2f3b3","entry":"Graph","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bbb5e685ad2f3b3"}},{"code_sha256_prefix":"90735a76fd308958","entry":"HYSP","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90735a76fd308958"}},{"code_sha256_prefix":"80f6560d69b89e68","entry":"HyperMapper","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80f6560d69b89e68"}},{"code_sha256_prefix":"3a7a63e8f839cd58","entry":"MLP","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a7a63e8f839cd58"}},{"code_sha256_prefix":"3b892a99281475cb","entry":"MobiusLinear","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b892a99281475cb"}},{"code_sha256_prefix":"45cf805fdfb46a6c","entry":"PositiveOnlyLoss","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45cf805fdfb46a6c"}},{"code_sha256_prefix":"bc7290a25a803047","entry":"_mobius_matvec","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc7290a25a803047"}},{"code_sha256_prefix":"59823bc0371d269d","entry":"mobius_linear","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59823bc0371d269d"}},{"code_sha256_prefix":"46dd9b384ab6543c","entry":"mobius_matvec","repo":"paolomandica/hysp","repo_kind":"official","path":"src/net/hysp.py","file_url":"https://github.com/paolomandica/hysp/blob/HEAD/src/net/hysp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46dd9b384ab6543c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}