{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MVK5WNQYI3DWMUNEZGTGLZZBKB","short_pith_number":"pith:MVK5WNQY","schema_version":"1.0","canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","source":{"kind":"arxiv","id":"2112.10482","version":3},"attestation_state":"computed","paper":{"title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Azuma, Motoaki Kawanabe, Shuhei Kurita, Taiki Miyanishi","submitted_at":"2021-12-20T12:30:55Z","abstract_excerpt":"We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals "},"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":"2112.10482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T12:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"a40790926c8c8445915e6ef145da09303e9b0c220805b743219fceb151871ec6","abstract_canon_sha256":"6dd25ad7d67a09652bb6000dbb17be5ca34eeefb56ff93f6d49fdd4750728a72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:08.288373Z","signature_b64":"6vGkvB6bQZDtgxoDWWDUFjWX2aDMDbBbsHJvmSbK3gJSvvf8wNsAim09MNzaYIcOpDkzX7nVy1rgRjBHDiFzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","last_reissued_at":"2026-07-05T04:21:08.287879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:08.287879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Azuma, Motoaki Kawanabe, Shuhei Kurita, Taiki Miyanishi","submitted_at":"2021-12-20T12:30:55Z","abstract_excerpt":"We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10482","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.10482/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":"2112.10482","created_at":"2026-07-05T04:21:08.287936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10482v3","created_at":"2026-07-05T04:21:08.287936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10482","created_at":"2026-07-05T04:21:08.287936+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVK5WNQYI3DW","created_at":"2026-07-05T04:21:08.287936+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVK5WNQYI3DWMUNE","created_at":"2026-07-05T04:21:08.287936+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVK5WNQY","created_at":"2026-07-05T04:21:08.287936+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/MVK5WNQYI3DWMUNEZGTGLZZBKB","json":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB.json","graph_json":"https://pith.science/api/pith-number/MVK5WNQYI3DWMUNEZGTGLZZBKB/graph.json","events_json":"https://pith.science/api/pith-number/MVK5WNQYI3DWMUNEZGTGLZZBKB/events.json","paper":"https://pith.science/paper/MVK5WNQY"},"agent_actions":{"view_html":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB","download_json":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB.json","view_paper":"https://pith.science/paper/MVK5WNQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10482&json=true","fetch_graph":"https://pith.science/api/pith-number/MVK5WNQYI3DWMUNEZGTGLZZBKB/graph.json","fetch_events":"https://pith.science/api/pith-number/MVK5WNQYI3DWMUNEZGTGLZZBKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/action/storage_attestation","attest_author":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/action/author_attestation","sign_citation":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/action/citation_signature","submit_replication":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/action/replication_record"}},"created_at":"2026-07-05T04:21:08.287936+00:00","updated_at":"2026-07-05T04:21:08.287936+00:00"}