{"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/masked-spatio-temporal-structure-prediction","title":"Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos","arxiv_id":"2308.09245","date":"2023-08-18","proceeding":"ICCV 2023 1","authors":["Zhiqiang Shen","Xiaoxiao Sheng","Hehe Fan","Longguang Wang","Yulan Guo","Qiong Liu","Hao Wen","Xi Zhou"],"abstract":"Recently, the community has made tremendous progress in developing effective methods for point cloud video understanding that learn from massive amounts of labeled data. However, annotating point cloud videos is usually notoriously expensive. Moreover, training via one or only a few traditional tasks (e.g., classification) may be insufficient to learn subtle details of the spatio-temporal structure existing in point cloud videos. In this paper, we propose a Masked Spatio-Temporal Structure Prediction (MaST-Pre) method to capture the structure of point cloud videos without human annotations. MaST-Pre is based on spatio-temporal point-tube masking and consists of two self-supervised learning tasks. First, by reconstructing masked point tubes, our method is able to capture the appearance information of point cloud videos. Second, to learn motion, we propose a temporal cardinality difference prediction task that estimates the change in the number of points within a point tube. In this way, MaST-Pre is forced to model the spatial and temporal structure in point cloud videos. Extensive experiments on MSRAction-3D, NTU-RGBD, NvGesture, and SHREC'17 demonstrate the effectiveness of the proposed method.","url_abs":"https://arxiv.org/abs/2308.09245v1","url_pdf":"https://arxiv.org/pdf/2308.09245v1.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":"masked-spatio-temporal-structure-prediction","repo_url":"https://github.com/johnsonsign/mast-pre","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"point-cloud-video-understanding","task_name":"point cloud video understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.09245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09245"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/johnsonsign/mast-pre","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":5,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":"b0f936d4d6ae3b8c","entry":"accuracy","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"utils.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0f936d4d6ae3b8c"}},{"code_sha256_prefix":"afa45bce6c6df7d7","entry":"eva_accuracy","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"utils.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"afa45bce6c6df7d7"}},{"code_sha256_prefix":"0c84b859d6153ecc","entry":"getDescribe","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"modules/SHOT.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/modules/SHOT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c84b859d6153ecc"}},{"code_sha256_prefix":"63986f88db53275c","entry":"getDescriptorLength","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"modules/SHOT.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/modules/SHOT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63986f88db53275c"}},{"code_sha256_prefix":"64392135fd38d38f","entry":"kaiming_uniform","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"modules/pst_convolutions.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/modules/pst_convolutions.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64392135fd38d38f"}},{"code_sha256_prefix":"430c25f4b5ea3a29","entry":"setup_logger","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"logger.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/logger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"430c25f4b5ea3a29"}},{"code_sha256_prefix":"2bb0eb60717758a7","entry":"uniform","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"modules/pst_convolutions.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/modules/pst_convolutions.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bb0eb60717758a7"}},{"code_sha256_prefix":"f4d486924b3f18c7","entry":"getSHOTLocalRF","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"modules/SHOT.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/modules/SHOT.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":"f4d486924b3f18c7"}},{"code_sha256_prefix":"5f0f7c378e04ba6a","entry":"reduce_tensor","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"utils.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/utils.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":"5f0f7c378e04ba6a"}},{"code_sha256_prefix":"0ad12b1e8408e2f9","entry":"set_bn_momentum_default","repo":"johnsonsign/mast-pre","repo_kind":"official","path":"modules/pytorch_utils.py","file_url":"https://github.com/johnsonsign/mast-pre/blob/HEAD/modules/pytorch_utils.py","link_basis":"harvester_set","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":"0ad12b1e8408e2f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}