{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RQMUOLEH3WIXNR4RIH6BHIGYKM","short_pith_number":"pith:RQMUOLEH","schema_version":"1.0","canonical_sha256":"8c19472c87dd9176c79141fc13a0d853293bdb8cffd5ecfbe80e9d27d401fdaa","source":{"kind":"arxiv","id":"2210.00843","version":2},"attestation_state":"computed","paper":{"title":"Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Georgios Tziafas, Hamidreza Kasaei","submitted_at":"2022-10-03T12:08:09Z","abstract_excerpt":"The Vision Transformer (ViT) architecture has established its place in computer vision literature, however, training ViTs for RGB-D object recognition remains an understudied topic, viewed in recent literature only through the lens of multi-task pretraining in multiple vision modalities. Such approaches are often computationally intensive, relying on the scale of multiple pretraining datasets to align RGB with 3D information. In this work, we propose a simple yet strong recipe for transferring pretrained ViTs in RGB-D domains for 3D object recognition, focusing on fusing RGB and depth represen"},"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":"2210.00843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T12:08:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"bf2f745fd0859daae6e2c0cc6dbb9d27d89521693899b3098af0cf5519654000","abstract_canon_sha256":"1a1b54f5fe47eac0f01d12b01dc5632a0c0622195a27a89da58dd24cbb91a8e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:39.622098Z","signature_b64":"5OoM9l2SV7CbC4Z4CyBB4pvDMveVTmltVCfphyyH+8cjn43e0ODWW9be40B80dUOehCUboN5PpSkqenyaOCiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c19472c87dd9176c79141fc13a0d853293bdb8cffd5ecfbe80e9d27d401fdaa","last_reissued_at":"2026-07-05T05:48:39.621659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:39.621659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Georgios Tziafas, Hamidreza Kasaei","submitted_at":"2022-10-03T12:08:09Z","abstract_excerpt":"The Vision Transformer (ViT) architecture has established its place in computer vision literature, however, training ViTs for RGB-D object recognition remains an understudied topic, viewed in recent literature only through the lens of multi-task pretraining in multiple vision modalities. Such approaches are often computationally intensive, relying on the scale of multiple pretraining datasets to align RGB with 3D information. In this work, we propose a simple yet strong recipe for transferring pretrained ViTs in RGB-D domains for 3D object recognition, focusing on fusing RGB and depth represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00843","kind":"arxiv","version":2},"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/2210.00843/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":"2210.00843","created_at":"2026-07-05T05:48:39.621712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00843v2","created_at":"2026-07-05T05:48:39.621712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00843","created_at":"2026-07-05T05:48:39.621712+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQMUOLEH3WIX","created_at":"2026-07-05T05:48:39.621712+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQMUOLEH3WIXNR4R","created_at":"2026-07-05T05:48:39.621712+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQMUOLEH","created_at":"2026-07-05T05:48:39.621712+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/RQMUOLEH3WIXNR4RIH6BHIGYKM","json":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM.json","graph_json":"https://pith.science/api/pith-number/RQMUOLEH3WIXNR4RIH6BHIGYKM/graph.json","events_json":"https://pith.science/api/pith-number/RQMUOLEH3WIXNR4RIH6BHIGYKM/events.json","paper":"https://pith.science/paper/RQMUOLEH"},"agent_actions":{"view_html":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM","download_json":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM.json","view_paper":"https://pith.science/paper/RQMUOLEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00843&json=true","fetch_graph":"https://pith.science/api/pith-number/RQMUOLEH3WIXNR4RIH6BHIGYKM/graph.json","fetch_events":"https://pith.science/api/pith-number/RQMUOLEH3WIXNR4RIH6BHIGYKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM/action/storage_attestation","attest_author":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM/action/author_attestation","sign_citation":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM/action/citation_signature","submit_replication":"https://pith.science/pith/RQMUOLEH3WIXNR4RIH6BHIGYKM/action/replication_record"}},"created_at":"2026-07-05T05:48:39.621712+00:00","updated_at":"2026-07-05T05:48:39.621712+00:00"}