{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ELKHYHGBL72CSQLBEKLG7VZ3TS","short_pith_number":"pith:ELKHYHGB","schema_version":"1.0","canonical_sha256":"22d47c1cc15ff429416122966fd73b9c9767f517e944c66df8a5e2d4222d0696","source":{"kind":"arxiv","id":"2005.14169","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Modal and View Invariant Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ling Zhang, Longlong Jing, Mingyi He, Yingli Tian, Yucheng Chen","submitted_at":"2020-05-28T17:35:14Z","abstract_excerpt":"Most of the existing self-supervised feature learning methods for 3D data either learn 3D features from point cloud data or from multi-view images. By exploring the inherent multi-modality attributes of 3D objects, in this paper, we propose to jointly learn modal-invariant and view-invariant features from different modalities including image, point cloud, and mesh with heterogeneous networks for 3D data. In order to learn modal- and view-invariant features, we propose two types of constraints: cross-modal invariance constraint and cross-view invariant constraint. Cross-modal invariance constra"},"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":"2005.14169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T17:35:14Z","cross_cats_sorted":[],"title_canon_sha256":"07de54d1fbecf17d5e9583602adca621c386afd17a63be8e375f9bf20fcf6f14","abstract_canon_sha256":"b18b11f29e92d41e2ec58dda077a73829f6fb31aaff6f697fc7da310a012ed69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:28.639436Z","signature_b64":"KQu/xCo+kcprcmocJbCr0UbaIPVP7kBDVU6ew1EK653xsO05LFOL4K4YqsTm+d3FGSnhVpfwUKmyd3hd/5FJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22d47c1cc15ff429416122966fd73b9c9767f517e944c66df8a5e2d4222d0696","last_reissued_at":"2026-07-05T01:06:28.639063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:28.639063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Modal and View Invariant Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ling Zhang, Longlong Jing, Mingyi He, Yingli Tian, Yucheng Chen","submitted_at":"2020-05-28T17:35:14Z","abstract_excerpt":"Most of the existing self-supervised feature learning methods for 3D data either learn 3D features from point cloud data or from multi-view images. By exploring the inherent multi-modality attributes of 3D objects, in this paper, we propose to jointly learn modal-invariant and view-invariant features from different modalities including image, point cloud, and mesh with heterogeneous networks for 3D data. In order to learn modal- and view-invariant features, we propose two types of constraints: cross-modal invariance constraint and cross-view invariant constraint. Cross-modal invariance constra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14169","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/2005.14169/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":"2005.14169","created_at":"2026-07-05T01:06:28.639112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.14169v1","created_at":"2026-07-05T01:06:28.639112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14169","created_at":"2026-07-05T01:06:28.639112+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELKHYHGBL72C","created_at":"2026-07-05T01:06:28.639112+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELKHYHGBL72CSQLB","created_at":"2026-07-05T01:06:28.639112+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELKHYHGB","created_at":"2026-07-05T01:06:28.639112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17566","citing_title":"Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS","json":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS.json","graph_json":"https://pith.science/api/pith-number/ELKHYHGBL72CSQLBEKLG7VZ3TS/graph.json","events_json":"https://pith.science/api/pith-number/ELKHYHGBL72CSQLBEKLG7VZ3TS/events.json","paper":"https://pith.science/paper/ELKHYHGB"},"agent_actions":{"view_html":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS","download_json":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS.json","view_paper":"https://pith.science/paper/ELKHYHGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.14169&json=true","fetch_graph":"https://pith.science/api/pith-number/ELKHYHGBL72CSQLBEKLG7VZ3TS/graph.json","fetch_events":"https://pith.science/api/pith-number/ELKHYHGBL72CSQLBEKLG7VZ3TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS/action/storage_attestation","attest_author":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS/action/author_attestation","sign_citation":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS/action/citation_signature","submit_replication":"https://pith.science/pith/ELKHYHGBL72CSQLBEKLG7VZ3TS/action/replication_record"}},"created_at":"2026-07-05T01:06:28.639112+00:00","updated_at":"2026-07-05T01:06:28.639112+00:00"}