{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KTJUMLYUHH4SJ7SBZSTI5FPEIL","short_pith_number":"pith:KTJUMLYU","schema_version":"1.0","canonical_sha256":"54d3462f1439f924fe41cca68e95e442fddc60749e0eda3ac97cb1c4b67e5136","source":{"kind":"arxiv","id":"2404.09146","version":1},"attestation_state":"computed","paper":{"title":"Fusion-Mamba for Cross-modality Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Guodong Guo, Haodong Zhu, Juan Zhang, Shaohui Lin, Wenhao Dong, Xiaoyan Luo, Xuhui Liu, Yunhang Shen","submitted_at":"2024-04-14T05:28:46Z","abstract_excerpt":"Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different types of images or merge different backbone features through elaborated neural network modules. However, these methods neglect that modality disparities affect cross-modality fusion performance, as different modalities with different camera focal lengths, placements, and angles are hardly fused. In this paper, we investigate cross-modality fusion by associatin"},"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":"2404.09146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-14T05:28:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"509b137b830283bc39055994a529b84329286a4d83a345b830436cae51666122","abstract_canon_sha256":"98cdf0d566aa9ef55295334f8229f27dc228c501f6026ef08a586eba7226dbef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:18.044370Z","signature_b64":"fNSnZv5d0CIHzvU1Tu8oZug2LqYXwJgV0ngnyiCpBMLdom4RH4VtnQ8VGP0zCQbkFEjRoAr8j/Oa4gaOQuNoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d3462f1439f924fe41cca68e95e442fddc60749e0eda3ac97cb1c4b67e5136","last_reissued_at":"2026-07-05T11:41:18.043857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:18.043857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusion-Mamba for Cross-modality Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Guodong Guo, Haodong Zhu, Juan Zhang, Shaohui Lin, Wenhao Dong, Xiaoyan Luo, Xuhui Liu, Yunhang Shen","submitted_at":"2024-04-14T05:28:46Z","abstract_excerpt":"Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different types of images or merge different backbone features through elaborated neural network modules. However, these methods neglect that modality disparities affect cross-modality fusion performance, as different modalities with different camera focal lengths, placements, and angles are hardly fused. In this paper, we investigate cross-modality fusion by associatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09146","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/2404.09146/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":"2404.09146","created_at":"2026-07-05T11:41:18.043924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09146v1","created_at":"2026-07-05T11:41:18.043924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09146","created_at":"2026-07-05T11:41:18.043924+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTJUMLYUHH4S","created_at":"2026-07-05T11:41:18.043924+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTJUMLYUHH4SJ7SB","created_at":"2026-07-05T11:41:18.043924+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTJUMLYU","created_at":"2026-07-05T11:41:18.043924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14799","citing_title":"Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13621","citing_title":"WD-FQDet: Multispectral Detection Transformer via Wavelet Decomposition and Frequency-aware Query Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04675","citing_title":"Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13426","citing_title":"Event-Adaptive State Transition and Gated Fusion for RGB-Event Object Tracking","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL","json":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL.json","graph_json":"https://pith.science/api/pith-number/KTJUMLYUHH4SJ7SBZSTI5FPEIL/graph.json","events_json":"https://pith.science/api/pith-number/KTJUMLYUHH4SJ7SBZSTI5FPEIL/events.json","paper":"https://pith.science/paper/KTJUMLYU"},"agent_actions":{"view_html":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL","download_json":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL.json","view_paper":"https://pith.science/paper/KTJUMLYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09146&json=true","fetch_graph":"https://pith.science/api/pith-number/KTJUMLYUHH4SJ7SBZSTI5FPEIL/graph.json","fetch_events":"https://pith.science/api/pith-number/KTJUMLYUHH4SJ7SBZSTI5FPEIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL/action/storage_attestation","attest_author":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL/action/author_attestation","sign_citation":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL/action/citation_signature","submit_replication":"https://pith.science/pith/KTJUMLYUHH4SJ7SBZSTI5FPEIL/action/replication_record"}},"created_at":"2026-07-05T11:41:18.043924+00:00","updated_at":"2026-07-05T11:41:18.043924+00:00"}