{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SSVVFNM63L5CAYNXUBXPVPDGSS","short_pith_number":"pith:SSVVFNM6","schema_version":"1.0","canonical_sha256":"94ab52b59edafa2061b7a06efabc6694b3e65a548870ae90a3031817982ed378","source":{"kind":"arxiv","id":"2111.00273","version":4},"attestation_state":"computed","paper":{"title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Fang Qingyun, Han Dapeng, Wang Zhaokui","submitted_at":"2021-10-30T15:34:12Z","abstract_excerpt":"Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality feature fusion approach, named Cross-Modality Fusion Transformer (CFT) in this paper. Unlike prior CNNs-based works, guided by the transformer scheme, our network learns long-range dependencies and integrates global contextual information in the feature extraction stage. More importantly, by leveraging the self attention of the transformer, the network can natu"},"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":"2111.00273","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-10-30T15:34:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"10dfa6ab0788ab889a39b0c6f066cdcef86fdf20312f3c69872b241fc01f5d11","abstract_canon_sha256":"1cbecf8db4a173e89597d8ec8542125607f974ef02470d2c12cf3bc09b9ca866"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:55.529514Z","signature_b64":"ToF3x0xE4rXNF8CC4S0uvLNZxfZErOiG2UJaKdfy/nbTJDhxG8Po9kZqOGu9IZpd/PNGlbzB1Ooat59pPBJkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ab52b59edafa2061b7a06efabc6694b3e65a548870ae90a3031817982ed378","last_reissued_at":"2026-07-05T05:02:55.529103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:55.529103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Fang Qingyun, Han Dapeng, Wang Zhaokui","submitted_at":"2021-10-30T15:34:12Z","abstract_excerpt":"Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality feature fusion approach, named Cross-Modality Fusion Transformer (CFT) in this paper. Unlike prior CNNs-based works, guided by the transformer scheme, our network learns long-range dependencies and integrates global contextual information in the feature extraction stage. More importantly, by leveraging the self attention of the transformer, the network can natu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00273","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/2111.00273/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":"2111.00273","created_at":"2026-07-05T05:02:55.529165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00273v4","created_at":"2026-07-05T05:02:55.529165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00273","created_at":"2026-07-05T05:02:55.529165+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSVVFNM63L5C","created_at":"2026-07-05T05:02:55.529165+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSVVFNM63L5CAYNX","created_at":"2026-07-05T05:02:55.529165+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSVVFNM6","created_at":"2026-07-05T05:02:55.529165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08191","citing_title":"Dual-Correlation Hypergraph Network for Unaligned RGBT Video Object Detection and A Large-scale Benchmark","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11572","citing_title":"FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31015","citing_title":"Dual Sparse Aggregation Transformer for Multispectral Object Detection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30215","citing_title":"Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20667","citing_title":"LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2508.02384","citing_title":"SMART-Ship: A Comprehensive Synchronized Multi-modal Aligned Remote Sensing Targets Dataset and Benchmark for Berthed Ships Analysis","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09533","citing_title":"COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection","ref_index":19,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11234","citing_title":"Bridging the RGB-IR Gap: Consensus and Discrepancy Modeling for Text-Guided Multispectral Detection","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS","json":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS.json","graph_json":"https://pith.science/api/pith-number/SSVVFNM63L5CAYNXUBXPVPDGSS/graph.json","events_json":"https://pith.science/api/pith-number/SSVVFNM63L5CAYNXUBXPVPDGSS/events.json","paper":"https://pith.science/paper/SSVVFNM6"},"agent_actions":{"view_html":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS","download_json":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS.json","view_paper":"https://pith.science/paper/SSVVFNM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00273&json=true","fetch_graph":"https://pith.science/api/pith-number/SSVVFNM63L5CAYNXUBXPVPDGSS/graph.json","fetch_events":"https://pith.science/api/pith-number/SSVVFNM63L5CAYNXUBXPVPDGSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS/action/storage_attestation","attest_author":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS/action/author_attestation","sign_citation":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS/action/citation_signature","submit_replication":"https://pith.science/pith/SSVVFNM63L5CAYNXUBXPVPDGSS/action/replication_record"}},"created_at":"2026-07-05T05:02:55.529165+00:00","updated_at":"2026-07-05T05:02:55.529165+00:00"}