{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2C7S5TQFLS4PAIPYJCQRHQYOX","short_pith_number":"pith:U2C7S5TQ","schema_version":"1.0","canonical_sha256":"a685f976702ae5c7810fc245089e1875f850f7595823bca6284bdc9e6b8839d6","source":{"kind":"arxiv","id":"2504.12576","version":1},"attestation_state":"computed","paper":{"title":"CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Chenglong Li, Jin Tang, Qi Liu, Wentao Wu, Xiao Wang","submitted_at":"2025-04-17T01:49:46Z","abstract_excerpt":"Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. Some researchers have begun exploring pre-training directly on event data. Nevertheless, these efforts often fail to establish strong connections with RGB frames, limiting their applicability in multi-modal fusion scenarios. To address these issues, we propose a novel CM3AE pre-training framework for the RGB-Event perception. This framework accepts multi-modalities/views of data as input, including RGB images, event i"},"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":"2504.12576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T01:49:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d3913cc3ed6aceebd648c91070ecf910acf036a9de74bbd8059e6f5dedc7ffd0","abstract_canon_sha256":"b2cb75684b28050be50ff4eb78dafca9a66bdb946b2b7691e1e79f99a070d95d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:18.808057Z","signature_b64":"YTCCOGqeD52dqp6U28qAQKu2pdmsjX1t40w5StjeHVXGhH0g6s/GtQwAJEwNxNL0OeZqqhE7+sz/Aq5e5t+0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a685f976702ae5c7810fc245089e1875f850f7595823bca6284bdc9e6b8839d6","last_reissued_at":"2026-07-05T10:50:18.807506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:18.807506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Chenglong Li, Jin Tang, Qi Liu, Wentao Wu, Xiao Wang","submitted_at":"2025-04-17T01:49:46Z","abstract_excerpt":"Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. Some researchers have begun exploring pre-training directly on event data. Nevertheless, these efforts often fail to establish strong connections with RGB frames, limiting their applicability in multi-modal fusion scenarios. To address these issues, we propose a novel CM3AE pre-training framework for the RGB-Event perception. This framework accepts multi-modalities/views of data as input, including RGB images, event i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12576","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/2504.12576/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":"2504.12576","created_at":"2026-07-05T10:50:18.807569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12576v1","created_at":"2026-07-05T10:50:18.807569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12576","created_at":"2026-07-05T10:50:18.807569+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2C7S5TQFLS4","created_at":"2026-07-05T10:50:18.807569+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2C7S5TQFLS4PAIP","created_at":"2026-07-05T10:50:18.807569+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2C7S5TQ","created_at":"2026-07-05T10:50:18.807569+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/U2C7S5TQFLS4PAIPYJCQRHQYOX","json":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX.json","graph_json":"https://pith.science/api/pith-number/U2C7S5TQFLS4PAIPYJCQRHQYOX/graph.json","events_json":"https://pith.science/api/pith-number/U2C7S5TQFLS4PAIPYJCQRHQYOX/events.json","paper":"https://pith.science/paper/U2C7S5TQ"},"agent_actions":{"view_html":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX","download_json":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX.json","view_paper":"https://pith.science/paper/U2C7S5TQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12576&json=true","fetch_graph":"https://pith.science/api/pith-number/U2C7S5TQFLS4PAIPYJCQRHQYOX/graph.json","fetch_events":"https://pith.science/api/pith-number/U2C7S5TQFLS4PAIPYJCQRHQYOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX/action/storage_attestation","attest_author":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX/action/author_attestation","sign_citation":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX/action/citation_signature","submit_replication":"https://pith.science/pith/U2C7S5TQFLS4PAIPYJCQRHQYOX/action/replication_record"}},"created_at":"2026-07-05T10:50:18.807569+00:00","updated_at":"2026-07-05T10:50:18.807569+00:00"}