{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C4TB66M4UUDKKXJNBOBRZTAIMJ","short_pith_number":"pith:C4TB66M4","schema_version":"1.0","canonical_sha256":"17261f799ca506a55d2d0b831ccc08624104e78245f39c1ef358db2b0367e4c0","source":{"kind":"arxiv","id":"2606.29136","version":1},"attestation_state":"computed","paper":{"title":"CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiangming Chen, Yanming Guo, Yingmei Wei, Yuenan Hou, Yu Li","submitted_at":"2026-06-28T00:49:05Z","abstract_excerpt":"Event cameras capture sparse brightness changes with high temporal resolution and high dynamic range, compensating for the deficiencies of the conventional RGB frames. However, previous multi-modal fusion techniques typically fail to handle the inherent heterogeneity between RGB frames and event streams, thus easily leading to noise amplification or redundant feature integration during cross-modal fusion. In this paper, we propose a Cross-Modal information inTeraction transFormer, coined as CMTFormer, which hierarchically integrates RGB and event information to achieve efficient and stable mul"},"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":"2606.29136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T00:49:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a39ad8c147727f32a177abbbaa728d5388bc55ac81e16e441e0316e5ed16324d","abstract_canon_sha256":"318f2d54ab2e56647684fa6525a35731272e1af1cafca2bfef6a206c32549dbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:54.031930Z","signature_b64":"tXv12znTDI6hvEH/Ko+s+NfUWdHdLpYvGkW7dyYSnFF+/ylNYIOl4GE7QtC8eWZRFjjOvmQxPBtQRTSlDjYEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17261f799ca506a55d2d0b831ccc08624104e78245f39c1ef358db2b0367e4c0","last_reissued_at":"2026-06-30T01:17:54.031443Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:54.031443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiangming Chen, Yanming Guo, Yingmei Wei, Yuenan Hou, Yu Li","submitted_at":"2026-06-28T00:49:05Z","abstract_excerpt":"Event cameras capture sparse brightness changes with high temporal resolution and high dynamic range, compensating for the deficiencies of the conventional RGB frames. However, previous multi-modal fusion techniques typically fail to handle the inherent heterogeneity between RGB frames and event streams, thus easily leading to noise amplification or redundant feature integration during cross-modal fusion. In this paper, we propose a Cross-Modal information inTeraction transFormer, coined as CMTFormer, which hierarchically integrates RGB and event information to achieve efficient and stable mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29136","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/2606.29136/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":"2606.29136","created_at":"2026-06-30T01:17:54.031522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29136v1","created_at":"2026-06-30T01:17:54.031522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29136","created_at":"2026-06-30T01:17:54.031522+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4TB66M4UUDK","created_at":"2026-06-30T01:17:54.031522+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4TB66M4UUDKKXJN","created_at":"2026-06-30T01:17:54.031522+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4TB66M4","created_at":"2026-06-30T01:17:54.031522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ","json":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ.json","graph_json":"https://pith.science/api/pith-number/C4TB66M4UUDKKXJNBOBRZTAIMJ/graph.json","events_json":"https://pith.science/api/pith-number/C4TB66M4UUDKKXJNBOBRZTAIMJ/events.json","paper":"https://pith.science/paper/C4TB66M4"},"agent_actions":{"view_html":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ","download_json":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ.json","view_paper":"https://pith.science/paper/C4TB66M4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29136&json=true","fetch_graph":"https://pith.science/api/pith-number/C4TB66M4UUDKKXJNBOBRZTAIMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C4TB66M4UUDKKXJNBOBRZTAIMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ/action/storage_attestation","attest_author":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ/action/author_attestation","sign_citation":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ/action/citation_signature","submit_replication":"https://pith.science/pith/C4TB66M4UUDKKXJNBOBRZTAIMJ/action/replication_record"}},"created_at":"2026-06-30T01:17:54.031522+00:00","updated_at":"2026-06-30T01:17:54.031522+00:00"}