{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOLAH5EL66TL2WZPLU6MXTXNGK","short_pith_number":"pith:TOLAH5EL","schema_version":"1.0","canonical_sha256":"9b9603f48bf7a6bd5b2f5d3ccbceed32a1bdea4752e4751e3e99db384bf08094","source":{"kind":"arxiv","id":"2503.11780","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Multi-Modal Object Detection from the Perspective of Mono-Modality Feature Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyang Liu, Maoxun Yuan, Tianyi Zhao, Xingxing Wei, Yanglei Gao, Yiming Sun","submitted_at":"2025-03-14T18:15:53Z","abstract_excerpt":"Multi-Modal Object Detection (MMOD), due to its stronger adaptability to various complex environments, has been widely applied in various applications. Extensive research is dedicated to the RGB-IR object detection, primarily focusing on how to integrate complementary features from RGB-IR modalities. However, they neglect the mono-modality insufficient learning problem, which arises from decreased feature extraction capability in multi-modal joint learning. This leads to a prevalent but unreasonable phenomenon\\textemdash Fusion Degradation, which hinders the performance improvement of the MMOD"},"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":"2503.11780","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T18:15:53Z","cross_cats_sorted":[],"title_canon_sha256":"9e21ff93fb38a6dbff69f09e4ae758a47ffead7c4b9f2a58ac8da4cd532956c5","abstract_canon_sha256":"b17911a666cb5f30b9540a1058df54bde036f781b3d3cb7683b20fee549fbd65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:02.736711Z","signature_b64":"69n5rY5JZjfWj0A7YkPKGAt8ZumE4abGflWWSggEtevbV5fGFAyCBBsm13N73niGbRaHXNIFVw09c+mthSIhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b9603f48bf7a6bd5b2f5d3ccbceed32a1bdea4752e4751e3e99db384bf08094","last_reissued_at":"2026-07-05T11:44:02.736201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:02.736201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Multi-Modal Object Detection from the Perspective of Mono-Modality Feature Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyang Liu, Maoxun Yuan, Tianyi Zhao, Xingxing Wei, Yanglei Gao, Yiming Sun","submitted_at":"2025-03-14T18:15:53Z","abstract_excerpt":"Multi-Modal Object Detection (MMOD), due to its stronger adaptability to various complex environments, has been widely applied in various applications. Extensive research is dedicated to the RGB-IR object detection, primarily focusing on how to integrate complementary features from RGB-IR modalities. However, they neglect the mono-modality insufficient learning problem, which arises from decreased feature extraction capability in multi-modal joint learning. This leads to a prevalent but unreasonable phenomenon\\textemdash Fusion Degradation, which hinders the performance improvement of the MMOD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11780","kind":"arxiv","version":2},"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/2503.11780/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":"2503.11780","created_at":"2026-07-05T11:44:02.736261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11780v2","created_at":"2026-07-05T11:44:02.736261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11780","created_at":"2026-07-05T11:44:02.736261+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOLAH5EL66TL","created_at":"2026-07-05T11:44:02.736261+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOLAH5EL66TL2WZP","created_at":"2026-07-05T11:44:02.736261+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOLAH5EL","created_at":"2026-07-05T11:44:02.736261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16630","citing_title":"Tri-Modal Fusion Transformers for UAV-based Object Detection","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK","json":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK.json","graph_json":"https://pith.science/api/pith-number/TOLAH5EL66TL2WZPLU6MXTXNGK/graph.json","events_json":"https://pith.science/api/pith-number/TOLAH5EL66TL2WZPLU6MXTXNGK/events.json","paper":"https://pith.science/paper/TOLAH5EL"},"agent_actions":{"view_html":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK","download_json":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK.json","view_paper":"https://pith.science/paper/TOLAH5EL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11780&json=true","fetch_graph":"https://pith.science/api/pith-number/TOLAH5EL66TL2WZPLU6MXTXNGK/graph.json","fetch_events":"https://pith.science/api/pith-number/TOLAH5EL66TL2WZPLU6MXTXNGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK/action/storage_attestation","attest_author":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK/action/author_attestation","sign_citation":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK/action/citation_signature","submit_replication":"https://pith.science/pith/TOLAH5EL66TL2WZPLU6MXTXNGK/action/replication_record"}},"created_at":"2026-07-05T11:44:02.736261+00:00","updated_at":"2026-07-05T11:44:02.736261+00:00"}