{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S44R2WWAV4V2OG5FL56KYXNLA6","short_pith_number":"pith:S44R2WWA","schema_version":"1.0","canonical_sha256":"97391d5ac0af2ba71ba55f7cac5dab07b188421d6253988dc3417a24692172ea","source":{"kind":"arxiv","id":"2110.13083","version":1},"attestation_state":"computed","paper":{"title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ping Li, Shuo Chen, Tan Yu","submitted_at":"2021-10-25T16:23:25Z","abstract_excerpt":"Inspired by the great success achieved by CNN in image recognition, view-based methods applied CNNs to model the projected views for 3D object understanding and achieved excellent performance. Nevertheless, multi-view CNN models cannot model the communications between patches from different views, limiting its effectiveness in 3D object recognition. Inspired by the recent success gained by vision Transformer in image recognition, we propose a Multi-view Vision Transformer (MVT) for 3D object recognition. Since each patch feature in a Transformer block has a global reception field, it naturally"},"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":"2110.13083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-25T16:23:25Z","cross_cats_sorted":[],"title_canon_sha256":"5901e6ef92abbb72f9a2d3de89228c23487f98ed5f29a631c5c3af796008b1dd","abstract_canon_sha256":"08b144ae803b70b6898419b1155a392953cbc18f66abc10e40c76370ae24cf90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:26.898196Z","signature_b64":"J8xqe4D1ldfX2LRFMSzN26DnZpQsbvLFu7Ky+c8JBWr+Gvmgu0yCnOaxMLP6PdwC92q5zqf/KR1RRNoIKy3qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97391d5ac0af2ba71ba55f7cac5dab07b188421d6253988dc3417a24692172ea","last_reissued_at":"2026-07-05T03:25:26.897774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:26.897774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ping Li, Shuo Chen, Tan Yu","submitted_at":"2021-10-25T16:23:25Z","abstract_excerpt":"Inspired by the great success achieved by CNN in image recognition, view-based methods applied CNNs to model the projected views for 3D object understanding and achieved excellent performance. Nevertheless, multi-view CNN models cannot model the communications between patches from different views, limiting its effectiveness in 3D object recognition. Inspired by the recent success gained by vision Transformer in image recognition, we propose a Multi-view Vision Transformer (MVT) for 3D object recognition. Since each patch feature in a Transformer block has a global reception field, it naturally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13083","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/2110.13083/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":"2110.13083","created_at":"2026-07-05T03:25:26.897832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13083v1","created_at":"2026-07-05T03:25:26.897832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13083","created_at":"2026-07-05T03:25:26.897832+00:00"},{"alias_kind":"pith_short_12","alias_value":"S44R2WWAV4V2","created_at":"2026-07-05T03:25:26.897832+00:00"},{"alias_kind":"pith_short_16","alias_value":"S44R2WWAV4V2OG5F","created_at":"2026-07-05T03:25:26.897832+00:00"},{"alias_kind":"pith_short_8","alias_value":"S44R2WWA","created_at":"2026-07-05T03:25:26.897832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19838","citing_title":"OTCHA: Optimal Transport-driven Confidence-aware Latent Hub Alignment for Multi-View Medical Image Classification","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6","json":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6.json","graph_json":"https://pith.science/api/pith-number/S44R2WWAV4V2OG5FL56KYXNLA6/graph.json","events_json":"https://pith.science/api/pith-number/S44R2WWAV4V2OG5FL56KYXNLA6/events.json","paper":"https://pith.science/paper/S44R2WWA"},"agent_actions":{"view_html":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6","download_json":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6.json","view_paper":"https://pith.science/paper/S44R2WWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13083&json=true","fetch_graph":"https://pith.science/api/pith-number/S44R2WWAV4V2OG5FL56KYXNLA6/graph.json","fetch_events":"https://pith.science/api/pith-number/S44R2WWAV4V2OG5FL56KYXNLA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6/action/storage_attestation","attest_author":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6/action/author_attestation","sign_citation":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6/action/citation_signature","submit_replication":"https://pith.science/pith/S44R2WWAV4V2OG5FL56KYXNLA6/action/replication_record"}},"created_at":"2026-07-05T03:25:26.897832+00:00","updated_at":"2026-07-05T03:25:26.897832+00:00"}