{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:REHB3VSQF2VZYJC2EBSZBOK7OI","short_pith_number":"pith:REHB3VSQ","schema_version":"1.0","canonical_sha256":"890e1dd6502eab9c245a206590b95f7202cf19ca13d7eaf7ea23b69ab16c3344","source":{"kind":"arxiv","id":"2408.09122","version":1},"attestation_state":"computed","paper":{"title":"MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Yang, Lihua Zhang, Mingcheng Li, Mingyang Sun, Shunli Wang, Xiao Zhao, Xukun Zhang","submitted_at":"2024-08-17T07:11:38Z","abstract_excerpt":"Accurate and robust multimodal multi-task perception is crucial for modern autonomous driving systems. However, current multimodal perception research follows independent paradigms designed for specific perception tasks, leading to a lack of complementary learning among tasks and decreased performance in multi-task learning (MTL) due to joint training. In this paper, we propose MaskBEV, a masked attention-based MTL paradigm that unifies 3D object detection and bird's eye view (BEV) map segmentation. MaskBEV introduces a task-agnostic Transformer decoder to process these diverse tasks, enabling"},"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":"2408.09122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-17T07:11:38Z","cross_cats_sorted":[],"title_canon_sha256":"7df50d27bd560fa5a9ec4c06f3b35bc285e77972a2ef2d7306967a627c0bb23a","abstract_canon_sha256":"0028cb1adcdc0ae22b5f852ebb9b650d8f7c42c136ae2ccf42d4892c9f9cf5a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:28.364019Z","signature_b64":"6QT6+8rgH6wGhHcg6kZsZEsb6N17Q0ZO6lhs61KgHZoV1KGPUVQhRVKYNETXwNyPGx0TvAkBJNn2NG6UDQs5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"890e1dd6502eab9c245a206590b95f7202cf19ca13d7eaf7ea23b69ab16c3344","last_reissued_at":"2026-07-05T08:56:28.363587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:28.363587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Yang, Lihua Zhang, Mingcheng Li, Mingyang Sun, Shunli Wang, Xiao Zhao, Xukun Zhang","submitted_at":"2024-08-17T07:11:38Z","abstract_excerpt":"Accurate and robust multimodal multi-task perception is crucial for modern autonomous driving systems. However, current multimodal perception research follows independent paradigms designed for specific perception tasks, leading to a lack of complementary learning among tasks and decreased performance in multi-task learning (MTL) due to joint training. In this paper, we propose MaskBEV, a masked attention-based MTL paradigm that unifies 3D object detection and bird's eye view (BEV) map segmentation. MaskBEV introduces a task-agnostic Transformer decoder to process these diverse tasks, enabling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09122","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/2408.09122/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":"2408.09122","created_at":"2026-07-05T08:56:28.363643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09122v1","created_at":"2026-07-05T08:56:28.363643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09122","created_at":"2026-07-05T08:56:28.363643+00:00"},{"alias_kind":"pith_short_12","alias_value":"REHB3VSQF2VZ","created_at":"2026-07-05T08:56:28.363643+00:00"},{"alias_kind":"pith_short_16","alias_value":"REHB3VSQF2VZYJC2","created_at":"2026-07-05T08:56:28.363643+00:00"},{"alias_kind":"pith_short_8","alias_value":"REHB3VSQ","created_at":"2026-07-05T08:56:28.363643+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":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI","json":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI.json","graph_json":"https://pith.science/api/pith-number/REHB3VSQF2VZYJC2EBSZBOK7OI/graph.json","events_json":"https://pith.science/api/pith-number/REHB3VSQF2VZYJC2EBSZBOK7OI/events.json","paper":"https://pith.science/paper/REHB3VSQ"},"agent_actions":{"view_html":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI","download_json":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI.json","view_paper":"https://pith.science/paper/REHB3VSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09122&json=true","fetch_graph":"https://pith.science/api/pith-number/REHB3VSQF2VZYJC2EBSZBOK7OI/graph.json","fetch_events":"https://pith.science/api/pith-number/REHB3VSQF2VZYJC2EBSZBOK7OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI/action/storage_attestation","attest_author":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI/action/author_attestation","sign_citation":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI/action/citation_signature","submit_replication":"https://pith.science/pith/REHB3VSQF2VZYJC2EBSZBOK7OI/action/replication_record"}},"created_at":"2026-07-05T08:56:28.363643+00:00","updated_at":"2026-07-05T08:56:28.363643+00:00"}