{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:33AO2IVKXOHI2TCOIX2LTRYPLC","short_pith_number":"pith:33AO2IVK","schema_version":"1.0","canonical_sha256":"dec0ed22aabb8e8d4c4e45f4b9c70f58893ce07e87bfb255c0174743aea80d03","source":{"kind":"arxiv","id":"1904.07601","version":3},"attestation_state":"computed","paper":{"title":"Relation-Shape Convolutional Neural Network for Point Cloud Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CG","cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bin Fan, Chunhong Pan, Shiming Xiang, Yongcheng Liu","submitted_at":"2019-04-16T11:28:51Z","abstract_excerpt":"Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an i"},"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":"1904.07601","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-16T11:28:51Z","cross_cats_sorted":["cs.AI","cs.CG","cs.GR","cs.RO"],"title_canon_sha256":"a94f6903e4f3d39fbef3378cd695f6cdc022d9b1ba59256f4e23eb9dee4837d2","abstract_canon_sha256":"fd3bc117dc17d12d2c5712ef696a6938586782eff6de99e0d86b54d68c95fa1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:08.986328Z","signature_b64":"NR6SPBhM6+0LJku6i/yVn4g1k5x+lln5VFek+t18qDgeEJGW8ezwoUQq9YU7eHKrysy9WtNj403xgrR8Lu6ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dec0ed22aabb8e8d4c4e45f4b9c70f58893ce07e87bfb255c0174743aea80d03","last_reissued_at":"2026-05-17T23:45:08.985734Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:08.985734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relation-Shape Convolutional Neural Network for Point Cloud Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CG","cs.GR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bin Fan, Chunhong Pan, Shiming Xiang, Yongcheng Liu","submitted_at":"2019-04-16T11:28:51Z","abstract_excerpt":"Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07601","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1904.07601","created_at":"2026-05-17T23:45:08.985853+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07601v3","created_at":"2026-05-17T23:45:08.985853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07601","created_at":"2026-05-17T23:45:08.985853+00:00"},{"alias_kind":"pith_short_12","alias_value":"33AO2IVKXOHI","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"33AO2IVKXOHI2TCO","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"33AO2IVK","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.03830","citing_title":"MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC","json":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC.json","graph_json":"https://pith.science/api/pith-number/33AO2IVKXOHI2TCOIX2LTRYPLC/graph.json","events_json":"https://pith.science/api/pith-number/33AO2IVKXOHI2TCOIX2LTRYPLC/events.json","paper":"https://pith.science/paper/33AO2IVK"},"agent_actions":{"view_html":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC","download_json":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC.json","view_paper":"https://pith.science/paper/33AO2IVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07601&json=true","fetch_graph":"https://pith.science/api/pith-number/33AO2IVKXOHI2TCOIX2LTRYPLC/graph.json","fetch_events":"https://pith.science/api/pith-number/33AO2IVKXOHI2TCOIX2LTRYPLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC/action/storage_attestation","attest_author":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC/action/author_attestation","sign_citation":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC/action/citation_signature","submit_replication":"https://pith.science/pith/33AO2IVKXOHI2TCOIX2LTRYPLC/action/replication_record"}},"created_at":"2026-05-17T23:45:08.985853+00:00","updated_at":"2026-05-17T23:45:08.985853+00:00"}