{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XQKEW37VRY6ZSKQWNWU4XUTL7D","short_pith_number":"pith:XQKEW37V","schema_version":"1.0","canonical_sha256":"bc144b6ff58e3d992a166da9cbd26bf8e65f7a63043829c22e92a619e7a4d7e4","source":{"kind":"arxiv","id":"1912.08830","version":3},"attestation_state":"computed","paper":{"title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Dave Zhenyu Chen, Matthias Nie{\\ss}ner","submitted_at":"2019-12-18T19:00:49Z","abstract_excerpt":"We introduce the task of 3D object localization in RGB-D scans using natural language descriptions. As input, we assume a point cloud of a scanned 3D scene along with a free-form description of a specified target object. To address this task, we propose ScanRefer, learning a fused descriptor from 3D object proposals and encoded sentence embeddings. This fused descriptor correlates language expressions with geometric features, enabling regression of the 3D bounding box of a target object. We also introduce the ScanRefer dataset, containing 51,583 descriptions of 11,046 objects from 800 ScanNet "},"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":"1912.08830","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-18T19:00:49Z","cross_cats_sorted":["cs.CL","cs.LG","eess.IV"],"title_canon_sha256":"6df8dd82f1596d2316591e982e837623e867f0cd1cf3423f953736d3f4cc8fc8","abstract_canon_sha256":"5238382285ca7dffa9012c28c67b354f50653083a225f1ff157d728c7e7a26cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:57.654469Z","signature_b64":"V6Bx6TcV6qDIOrsGn7i126OzQLu95LLA0XxWkHJmoLPJ9Qr1Bzw/Ml6CsPuhPbgSdPAcW+FV3CRQJnWbxNd+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc144b6ff58e3d992a166da9cbd26bf8e65f7a63043829c22e92a619e7a4d7e4","last_reissued_at":"2026-07-05T01:50:57.653926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:57.653926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Dave Zhenyu Chen, Matthias Nie{\\ss}ner","submitted_at":"2019-12-18T19:00:49Z","abstract_excerpt":"We introduce the task of 3D object localization in RGB-D scans using natural language descriptions. As input, we assume a point cloud of a scanned 3D scene along with a free-form description of a specified target object. To address this task, we propose ScanRefer, learning a fused descriptor from 3D object proposals and encoded sentence embeddings. This fused descriptor correlates language expressions with geometric features, enabling regression of the 3D bounding box of a target object. We also introduce the ScanRefer dataset, containing 51,583 descriptions of 11,046 objects from 800 ScanNet "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08830","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/1912.08830/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":"1912.08830","created_at":"2026-07-05T01:50:57.653984+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.08830v3","created_at":"2026-07-05T01:50:57.653984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08830","created_at":"2026-07-05T01:50:57.653984+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQKEW37VRY6Z","created_at":"2026-07-05T01:50:57.653984+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQKEW37VRY6ZSKQW","created_at":"2026-07-05T01:50:57.653984+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQKEW37V","created_at":"2026-07-05T01:50:57.653984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21788","citing_title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08096","citing_title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D","json":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D.json","graph_json":"https://pith.science/api/pith-number/XQKEW37VRY6ZSKQWNWU4XUTL7D/graph.json","events_json":"https://pith.science/api/pith-number/XQKEW37VRY6ZSKQWNWU4XUTL7D/events.json","paper":"https://pith.science/paper/XQKEW37V"},"agent_actions":{"view_html":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D","download_json":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D.json","view_paper":"https://pith.science/paper/XQKEW37V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.08830&json=true","fetch_graph":"https://pith.science/api/pith-number/XQKEW37VRY6ZSKQWNWU4XUTL7D/graph.json","fetch_events":"https://pith.science/api/pith-number/XQKEW37VRY6ZSKQWNWU4XUTL7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D/action/storage_attestation","attest_author":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D/action/author_attestation","sign_citation":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D/action/citation_signature","submit_replication":"https://pith.science/pith/XQKEW37VRY6ZSKQWNWU4XUTL7D/action/replication_record"}},"created_at":"2026-07-05T01:50:57.653984+00:00","updated_at":"2026-07-05T01:50:57.653984+00:00"}