{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CX4ATQXAAK7EEIJABA2D34ZCGM","short_pith_number":"pith:CX4ATQXA","schema_version":"1.0","canonical_sha256":"15f809c2e002be42212008343df322333371162e8f880723600c82560c40207b","source":{"kind":"arxiv","id":"2305.15765","version":1},"attestation_state":"computed","paper":{"title":"Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianbing Shen, Junbo Yin, Ruigang Yang, Wei Li, Wenhao Cheng","submitted_at":"2023-05-25T06:22:10Z","abstract_excerpt":"This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus on the 2D or 3D-indoor domain, which is not suitable for accurately predicting the location of the queried 3D region in an autonomous driving scene. In addition, the upper-bound limitation and the heavy computation cost motivate us to explore a better solution. In this work, we propose a new multi-modal visual grounding task, termed LiDAR Grounding. Then we "},"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":"2305.15765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T06:22:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b2d7cc325f4414eea0e8845caa1176c315036dddd202fabd1fe14ba2a7f79b0a","abstract_canon_sha256":"48cf80f29146e2a0f54d5e53f64cca9f4c269d8c88de9f68487495e7e01f2bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:44.544521Z","signature_b64":"YSf4PG0e7PNvk8B45yVxmzeLhD6Onrpn7UlgxrBV3/YQYQiSPIJc91r/LKae3dnhLBNymGkwwoYVZ97u4cL6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15f809c2e002be42212008343df322333371162e8f880723600c82560c40207b","last_reissued_at":"2026-07-05T06:13:44.543987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:44.543987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianbing Shen, Junbo Yin, Ruigang Yang, Wei Li, Wenhao Cheng","submitted_at":"2023-05-25T06:22:10Z","abstract_excerpt":"This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus on the 2D or 3D-indoor domain, which is not suitable for accurately predicting the location of the queried 3D region in an autonomous driving scene. In addition, the upper-bound limitation and the heavy computation cost motivate us to explore a better solution. In this work, we propose a new multi-modal visual grounding task, termed LiDAR Grounding. Then we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15765","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/2305.15765/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":"2305.15765","created_at":"2026-07-05T06:13:44.544043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15765v1","created_at":"2026-07-05T06:13:44.544043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15765","created_at":"2026-07-05T06:13:44.544043+00:00"},{"alias_kind":"pith_short_12","alias_value":"CX4ATQXAAK7E","created_at":"2026-07-05T06:13:44.544043+00:00"},{"alias_kind":"pith_short_16","alias_value":"CX4ATQXAAK7EEIJA","created_at":"2026-07-05T06:13:44.544043+00:00"},{"alias_kind":"pith_short_8","alias_value":"CX4ATQXA","created_at":"2026-07-05T06:13:44.544043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04568","citing_title":"Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM","json":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM.json","graph_json":"https://pith.science/api/pith-number/CX4ATQXAAK7EEIJABA2D34ZCGM/graph.json","events_json":"https://pith.science/api/pith-number/CX4ATQXAAK7EEIJABA2D34ZCGM/events.json","paper":"https://pith.science/paper/CX4ATQXA"},"agent_actions":{"view_html":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM","download_json":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM.json","view_paper":"https://pith.science/paper/CX4ATQXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15765&json=true","fetch_graph":"https://pith.science/api/pith-number/CX4ATQXAAK7EEIJABA2D34ZCGM/graph.json","fetch_events":"https://pith.science/api/pith-number/CX4ATQXAAK7EEIJABA2D34ZCGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM/action/storage_attestation","attest_author":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM/action/author_attestation","sign_citation":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM/action/citation_signature","submit_replication":"https://pith.science/pith/CX4ATQXAAK7EEIJABA2D34ZCGM/action/replication_record"}},"created_at":"2026-07-05T06:13:44.544043+00:00","updated_at":"2026-07-05T06:13:44.544043+00:00"}