{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E6JMC63IGNGJO5WSSDNBTGGNHU","short_pith_number":"pith:E6JMC63I","schema_version":"1.0","canonical_sha256":"2792c17b68334c9776d290da1998cd3d3f5b177d29809dc422cb0a4462ab8514","source":{"kind":"arxiv","id":"2112.08359","version":2},"attestation_state":"computed","paper":{"title":"3D Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Jing Liao, Shuquan Ye, Songfang Han","submitted_at":"2021-12-15T18:59:59Z","abstract_excerpt":"Visual Question Answering (VQA) has witnessed tremendous progress in recent years. However, most efforts only focus on the 2D image question answering tasks. In this paper, we present the first attempt at extending VQA to the 3D domain, which can facilitate artificial intelligence's perception of 3D real-world scenarios. Different from image based VQA, 3D Question Answering (3DQA) takes the color point cloud as input and requires both appearance and 3D geometry comprehension ability to answer the 3D-related questions. To this end, we propose a novel transformer-based 3DQA framework \"3DQA-TR\", "},"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":"2112.08359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-15T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"2abc14ee0a06a8e74f01966c5e75642e3cc4ed75131651447bc83c6fd2992dd3","abstract_canon_sha256":"b8902501cb65425bfa189b73502caa3bdf313ff8d5b1b86ee4ed4265bb3a4340"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:09.339997Z","signature_b64":"oJAZ/J1jOMKNXZ1E2lp+NEdX9bbPJKKzZvW562R2VbTKVyID+zLY28UywMCMcH3efoRXd3HK/xpmdANOUgtxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2792c17b68334c9776d290da1998cd3d3f5b177d29809dc422cb0a4462ab8514","last_reissued_at":"2026-07-05T05:20:09.339477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:09.339477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Jing Liao, Shuquan Ye, Songfang Han","submitted_at":"2021-12-15T18:59:59Z","abstract_excerpt":"Visual Question Answering (VQA) has witnessed tremendous progress in recent years. However, most efforts only focus on the 2D image question answering tasks. In this paper, we present the first attempt at extending VQA to the 3D domain, which can facilitate artificial intelligence's perception of 3D real-world scenarios. Different from image based VQA, 3D Question Answering (3DQA) takes the color point cloud as input and requires both appearance and 3D geometry comprehension ability to answer the 3D-related questions. To this end, we propose a novel transformer-based 3DQA framework \"3DQA-TR\", "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08359","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/2112.08359/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":"2112.08359","created_at":"2026-07-05T05:20:09.339536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08359v2","created_at":"2026-07-05T05:20:09.339536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08359","created_at":"2026-07-05T05:20:09.339536+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6JMC63IGNGJ","created_at":"2026-07-05T05:20:09.339536+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6JMC63IGNGJO5WS","created_at":"2026-07-05T05:20:09.339536+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6JMC63I","created_at":"2026-07-05T05:20:09.339536+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/E6JMC63IGNGJO5WSSDNBTGGNHU","json":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU.json","graph_json":"https://pith.science/api/pith-number/E6JMC63IGNGJO5WSSDNBTGGNHU/graph.json","events_json":"https://pith.science/api/pith-number/E6JMC63IGNGJO5WSSDNBTGGNHU/events.json","paper":"https://pith.science/paper/E6JMC63I"},"agent_actions":{"view_html":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU","download_json":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU.json","view_paper":"https://pith.science/paper/E6JMC63I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08359&json=true","fetch_graph":"https://pith.science/api/pith-number/E6JMC63IGNGJO5WSSDNBTGGNHU/graph.json","fetch_events":"https://pith.science/api/pith-number/E6JMC63IGNGJO5WSSDNBTGGNHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU/action/storage_attestation","attest_author":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU/action/author_attestation","sign_citation":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU/action/citation_signature","submit_replication":"https://pith.science/pith/E6JMC63IGNGJO5WSSDNBTGGNHU/action/replication_record"}},"created_at":"2026-07-05T05:20:09.339536+00:00","updated_at":"2026-07-05T05:20:09.339536+00:00"}