{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5AWIRHBPJBV5D3TGYV6WIAX3SS","short_pith_number":"pith:5AWIRHBP","schema_version":"1.0","canonical_sha256":"e82c889c2f486bd1ee66c57d6402fb94bcbe28b5c22e628ed4333de79862f533","source":{"kind":"arxiv","id":"2208.11112","version":4},"attestation_state":"computed","paper":{"title":"DeepInteraction: 3D Object Detection via Modality Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Chen, Li Zhang, Wei Li, Xiatian Zhu, Zeyu Yang, Zhenwei Miao","submitted_at":"2022-08-23T17:52:54Z","abstract_excerpt":"Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introduce a novel modality interaction strategy where individual per-modality representations are learned and maintained throughout for enabling their unique characteristics to be exploited during object detection. To realize this proposed strategy, we design a DeepInteraction architecture characterized by"},"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":"2208.11112","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-23T17:52:54Z","cross_cats_sorted":[],"title_canon_sha256":"d2be7ce447207d88e5b8ebe3b7ccc501a304aef8ad12a4a3012b2e7bcb3f1f84","abstract_canon_sha256":"c538f0b6e19dd605aef577a63ef0e6507052c13ed8e8bd7017cf9ff90ff26eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:32.723157Z","signature_b64":"xjCraxOLcKRLx/lERn6YJXH45bfPK09BDpkP33P1UqolPbhwOq7QdZaB1HaTNh2LGXlCJ9+IUboilkk1bRUfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82c889c2f486bd1ee66c57d6402fb94bcbe28b5c22e628ed4333de79862f533","last_reissued_at":"2026-07-05T05:23:32.722703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:32.722703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepInteraction: 3D Object Detection via Modality Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Chen, Li Zhang, Wei Li, Xiatian Zhu, Zeyu Yang, Zhenwei Miao","submitted_at":"2022-08-23T17:52:54Z","abstract_excerpt":"Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introduce a novel modality interaction strategy where individual per-modality representations are learned and maintained throughout for enabling their unique characteristics to be exploited during object detection. To realize this proposed strategy, we design a DeepInteraction architecture characterized by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11112","kind":"arxiv","version":4},"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/2208.11112/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":"2208.11112","created_at":"2026-07-05T05:23:32.722749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11112v4","created_at":"2026-07-05T05:23:32.722749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11112","created_at":"2026-07-05T05:23:32.722749+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AWIRHBPJBV5","created_at":"2026-07-05T05:23:32.722749+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AWIRHBPJBV5D3TG","created_at":"2026-07-05T05:23:32.722749+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AWIRHBP","created_at":"2026-07-05T05:23:32.722749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06550","citing_title":"CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS","json":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS.json","graph_json":"https://pith.science/api/pith-number/5AWIRHBPJBV5D3TGYV6WIAX3SS/graph.json","events_json":"https://pith.science/api/pith-number/5AWIRHBPJBV5D3TGYV6WIAX3SS/events.json","paper":"https://pith.science/paper/5AWIRHBP"},"agent_actions":{"view_html":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS","download_json":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS.json","view_paper":"https://pith.science/paper/5AWIRHBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11112&json=true","fetch_graph":"https://pith.science/api/pith-number/5AWIRHBPJBV5D3TGYV6WIAX3SS/graph.json","fetch_events":"https://pith.science/api/pith-number/5AWIRHBPJBV5D3TGYV6WIAX3SS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS/action/storage_attestation","attest_author":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS/action/author_attestation","sign_citation":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS/action/citation_signature","submit_replication":"https://pith.science/pith/5AWIRHBPJBV5D3TGYV6WIAX3SS/action/replication_record"}},"created_at":"2026-07-05T05:23:32.722749+00:00","updated_at":"2026-07-05T05:23:32.722749+00:00"}