{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PO5YXD3S6VWEIIKM4P5XYL53KW","short_pith_number":"pith:PO5YXD3S","schema_version":"1.0","canonical_sha256":"7bbb8b8f72f56c44214ce3fb7c2fbb55abde7ca60ba6b449c15bd39d1e08823a","source":{"kind":"arxiv","id":"2305.04075","version":1},"attestation_state":"computed","paper":{"title":"PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Longguang Wang, Qiong Liu, Xiaoxiao Sheng, Xi Zhou, Yulan Guo, Zhiqiang Shen","submitted_at":"2023-05-06T15:47:48Z","abstract_excerpt":"Self-supervised learning can extract representations of good quality from solely unlabeled data, which is appealing for point cloud videos due to their high labelling cost. In this paper, we propose a contrastive mask prediction (PointCMP) framework for self-supervised learning on point cloud videos. Specifically, our PointCMP employs a two-branch structure to achieve simultaneous learning of both local and global spatio-temporal information. On top of this two-branch structure, a mutual similarity based augmentation module is developed to synthesize hard samples at the feature level. By maski"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.04075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T15:47:48Z","cross_cats_sorted":[],"title_canon_sha256":"e9abff06cb4d9c1eac09c0217e7319976004bb963e32b719b23313d63eb2b38e","abstract_canon_sha256":"5bebbac5d133cab62eec493f51681c816ef720eb777aef94f126105eed65cda8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:44.559856Z","signature_b64":"m/ZjOTvQYviY1fNR4HWCXa+OVxgaSODsDOiZ/kpmApqjtXcshlQxLTuJ77D009I8bS1dl5BtackAqPPGJIEaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bbb8b8f72f56c44214ce3fb7c2fbb55abde7ca60ba6b449c15bd39d1e08823a","last_reissued_at":"2026-07-05T06:07:44.559384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:44.559384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Longguang Wang, Qiong Liu, Xiaoxiao Sheng, Xi Zhou, Yulan Guo, Zhiqiang Shen","submitted_at":"2023-05-06T15:47:48Z","abstract_excerpt":"Self-supervised learning can extract representations of good quality from solely unlabeled data, which is appealing for point cloud videos due to their high labelling cost. In this paper, we propose a contrastive mask prediction (PointCMP) framework for self-supervised learning on point cloud videos. Specifically, our PointCMP employs a two-branch structure to achieve simultaneous learning of both local and global spatio-temporal information. On top of this two-branch structure, a mutual similarity based augmentation module is developed to synthesize hard samples at the feature level. By maski"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04075","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.04075/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.04075","created_at":"2026-07-05T06:07:44.559440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04075v1","created_at":"2026-07-05T06:07:44.559440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04075","created_at":"2026-07-05T06:07:44.559440+00:00"},{"alias_kind":"pith_short_12","alias_value":"PO5YXD3S6VWE","created_at":"2026-07-05T06:07:44.559440+00:00"},{"alias_kind":"pith_short_16","alias_value":"PO5YXD3S6VWEIIKM","created_at":"2026-07-05T06:07:44.559440+00:00"},{"alias_kind":"pith_short_8","alias_value":"PO5YXD3S","created_at":"2026-07-05T06:07:44.559440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW","json":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW.json","graph_json":"https://pith.science/api/pith-number/PO5YXD3S6VWEIIKM4P5XYL53KW/graph.json","events_json":"https://pith.science/api/pith-number/PO5YXD3S6VWEIIKM4P5XYL53KW/events.json","paper":"https://pith.science/paper/PO5YXD3S"},"agent_actions":{"view_html":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW","download_json":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW.json","view_paper":"https://pith.science/paper/PO5YXD3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04075&json=true","fetch_graph":"https://pith.science/api/pith-number/PO5YXD3S6VWEIIKM4P5XYL53KW/graph.json","fetch_events":"https://pith.science/api/pith-number/PO5YXD3S6VWEIIKM4P5XYL53KW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW/action/storage_attestation","attest_author":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW/action/author_attestation","sign_citation":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW/action/citation_signature","submit_replication":"https://pith.science/pith/PO5YXD3S6VWEIIKM4P5XYL53KW/action/replication_record"}},"created_at":"2026-07-05T06:07:44.559440+00:00","updated_at":"2026-07-05T06:07:44.559440+00:00"}