{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HFTAQRZLDAJBOJLBR6WJZDDAG7","short_pith_number":"pith:HFTAQRZL","schema_version":"1.0","canonical_sha256":"396608472b18121725618fac9c8c6037d3d45e0ab84a8f5f9bff378c5223778f","source":{"kind":"arxiv","id":"2408.05945","version":2},"attestation_state":"computed","paper":{"title":"MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Naiyan Wang, Si Liu, Yulu Gao, Zehao Huang, Zitian Wang","submitted_at":"2024-08-12T06:46:05Z","abstract_excerpt":"The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generato"},"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":"2408.05945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-12T06:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"58ee510941c8451ec6feefff33b4635b3f5d89560263e14dbfbbf5182836d791","abstract_canon_sha256":"8a7b95de52241f1ef7d904bb35e0f89ce2a788d326223c8bc599180aeb052043"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:02.182297Z","signature_b64":"98mYpxj4extQMSOzQWSHvNwUNd3aDPHp46NN0I3dYFza+6/SX9yHSpP2unedUZrqnfJktxCffaaQ/EEDbxumCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"396608472b18121725618fac9c8c6037d3d45e0ab84a8f5f9bff378c5223778f","last_reissued_at":"2026-07-05T11:31:02.181789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:02.181789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Naiyan Wang, Si Liu, Yulu Gao, Zehao Huang, Zitian Wang","submitted_at":"2024-08-12T06:46:05Z","abstract_excerpt":"The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generato"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05945","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/2408.05945/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":"2408.05945","created_at":"2026-07-05T11:31:02.181850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05945v2","created_at":"2026-07-05T11:31:02.181850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05945","created_at":"2026-07-05T11:31:02.181850+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFTAQRZLDAJB","created_at":"2026-07-05T11:31:02.181850+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFTAQRZLDAJBOJLB","created_at":"2026-07-05T11:31:02.181850+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFTAQRZL","created_at":"2026-07-05T11:31:02.181850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00746","citing_title":"GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26641","citing_title":"All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles","ref_index":288,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7","json":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7.json","graph_json":"https://pith.science/api/pith-number/HFTAQRZLDAJBOJLBR6WJZDDAG7/graph.json","events_json":"https://pith.science/api/pith-number/HFTAQRZLDAJBOJLBR6WJZDDAG7/events.json","paper":"https://pith.science/paper/HFTAQRZL"},"agent_actions":{"view_html":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7","download_json":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7.json","view_paper":"https://pith.science/paper/HFTAQRZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05945&json=true","fetch_graph":"https://pith.science/api/pith-number/HFTAQRZLDAJBOJLBR6WJZDDAG7/graph.json","fetch_events":"https://pith.science/api/pith-number/HFTAQRZLDAJBOJLBR6WJZDDAG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7/action/storage_attestation","attest_author":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7/action/author_attestation","sign_citation":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7/action/citation_signature","submit_replication":"https://pith.science/pith/HFTAQRZLDAJBOJLBR6WJZDDAG7/action/replication_record"}},"created_at":"2026-07-05T11:31:02.181850+00:00","updated_at":"2026-07-05T11:31:02.181850+00:00"}