{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I23EVBPEBHVF3GUCWFPDFKLOZP","short_pith_number":"pith:I23EVBPE","schema_version":"1.0","canonical_sha256":"46b64a85e409ea5d9a82b15e32a96ecbe4d1f36bbd6fc8414265eeb973fdb335","source":{"kind":"arxiv","id":"2403.15241","version":1},"attestation_state":"computed","paper":{"title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbing Shen, Junbo Yin, Pascal Frossard, Ruigang Yang, Runnan Chen, Wei Li, Wenguan Wang","submitted_at":"2024-03-22T14:34:17Z","abstract_excerpt":"Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-Fusion, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-Fusion essentially differs from existing approaches that only focus on the BEV scene-level fusion by explicitly incorp"},"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":"2403.15241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T14:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"bd013b5de3ec8ea0a3949c5640a2f266c866834917fbffd00b97520dbd16fadf","abstract_canon_sha256":"45cbfa109bcc2a0703c78fd7da65525069da2b3c8ee971c838df4ccfcf9ce482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:32.280191Z","signature_b64":"xStYiDkpDsNi/rN5IVp9yHYHo5ivD5YIbqSzCJ06Ro0hlPGzMelIy6E5UG7KzYsAjn6oY2Dpby0TYcwqLiMeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46b64a85e409ea5d9a82b15e32a96ecbe4d1f36bbd6fc8414265eeb973fdb335","last_reissued_at":"2026-07-05T07:59:32.279784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:32.279784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbing Shen, Junbo Yin, Pascal Frossard, Ruigang Yang, Runnan Chen, Wei Li, Wenguan Wang","submitted_at":"2024-03-22T14:34:17Z","abstract_excerpt":"Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-Fusion, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-Fusion essentially differs from existing approaches that only focus on the BEV scene-level fusion by explicitly incorp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15241","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/2403.15241/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":"2403.15241","created_at":"2026-07-05T07:59:32.279845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15241v1","created_at":"2026-07-05T07:59:32.279845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15241","created_at":"2026-07-05T07:59:32.279845+00:00"},{"alias_kind":"pith_short_12","alias_value":"I23EVBPEBHVF","created_at":"2026-07-05T07:59:32.279845+00:00"},{"alias_kind":"pith_short_16","alias_value":"I23EVBPEBHVF3GUC","created_at":"2026-07-05T07:59:32.279845+00:00"},{"alias_kind":"pith_short_8","alias_value":"I23EVBPE","created_at":"2026-07-05T07:59:32.279845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00746","citing_title":"GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP","json":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP.json","graph_json":"https://pith.science/api/pith-number/I23EVBPEBHVF3GUCWFPDFKLOZP/graph.json","events_json":"https://pith.science/api/pith-number/I23EVBPEBHVF3GUCWFPDFKLOZP/events.json","paper":"https://pith.science/paper/I23EVBPE"},"agent_actions":{"view_html":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP","download_json":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP.json","view_paper":"https://pith.science/paper/I23EVBPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15241&json=true","fetch_graph":"https://pith.science/api/pith-number/I23EVBPEBHVF3GUCWFPDFKLOZP/graph.json","fetch_events":"https://pith.science/api/pith-number/I23EVBPEBHVF3GUCWFPDFKLOZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP/action/storage_attestation","attest_author":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP/action/author_attestation","sign_citation":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP/action/citation_signature","submit_replication":"https://pith.science/pith/I23EVBPEBHVF3GUCWFPDFKLOZP/action/replication_record"}},"created_at":"2026-07-05T07:59:32.279845+00:00","updated_at":"2026-07-05T07:59:32.279845+00:00"}