{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7A6QJASW575CGSXTZTF7MZFN2H","short_pith_number":"pith:7A6QJASW","schema_version":"1.0","canonical_sha256":"f83d048256effa234af3cccbf664add1ffd463adfccff25c1743bd2d7475c069","source":{"kind":"arxiv","id":"2312.11128","version":2},"attestation_state":"computed","paper":{"title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Jin Tang, Shiao Wang, Xiao Wang, Yao Rong, Yonghong Tian, Yuan Chen, Zhe Wu","submitted_at":"2023-12-18T11:58:03Z","abstract_excerpt":"Pattern recognition based on RGB-Event data is a newly arising research topic and previous works usually learn their features using CNN or Transformer. As we know, CNN captures the local features well and the cascaded self-attention mechanisms are good at extracting the long-range global relations. It is intuitive to combine them for high-performance RGB-Event based video recognition, however, existing works fail to achieve a good balance between the accuracy and model parameters, as shown in Fig.~\\ref{firstimage}. In this work, we propose a novel RGB-Event based recognition framework termed T"},"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":"2312.11128","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-18T11:58:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b902e4e90d7d47a0c64db5703f082ecb0c04f542ebb40e1004061b28b543e918","abstract_canon_sha256":"0a152c93b245594152c8a595c5aa594844d5157b6412868535b125286208b3d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:41.155973Z","signature_b64":"t7+essD2Z5lJOl19Srq07rgbytEieSOlb8bZJQZQz2EENRphbZs9D/t3EhqQEp09SGYEa+EnX79vSwjAyVIjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f83d048256effa234af3cccbf664add1ffd463adfccff25c1743bd2d7475c069","last_reissued_at":"2026-07-05T10:50:41.155471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:41.155471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Jin Tang, Shiao Wang, Xiao Wang, Yao Rong, Yonghong Tian, Yuan Chen, Zhe Wu","submitted_at":"2023-12-18T11:58:03Z","abstract_excerpt":"Pattern recognition based on RGB-Event data is a newly arising research topic and previous works usually learn their features using CNN or Transformer. As we know, CNN captures the local features well and the cascaded self-attention mechanisms are good at extracting the long-range global relations. It is intuitive to combine them for high-performance RGB-Event based video recognition, however, existing works fail to achieve a good balance between the accuracy and model parameters, as shown in Fig.~\\ref{firstimage}. In this work, we propose a novel RGB-Event based recognition framework termed T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11128","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/2312.11128/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":"2312.11128","created_at":"2026-07-05T10:50:41.155533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11128v2","created_at":"2026-07-05T10:50:41.155533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11128","created_at":"2026-07-05T10:50:41.155533+00:00"},{"alias_kind":"pith_short_12","alias_value":"7A6QJASW575C","created_at":"2026-07-05T10:50:41.155533+00:00"},{"alias_kind":"pith_short_16","alias_value":"7A6QJASW575CGSXT","created_at":"2026-07-05T10:50:41.155533+00:00"},{"alias_kind":"pith_short_8","alias_value":"7A6QJASW","created_at":"2026-07-05T10:50:41.155533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.18328","citing_title":"EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H","json":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H.json","graph_json":"https://pith.science/api/pith-number/7A6QJASW575CGSXTZTF7MZFN2H/graph.json","events_json":"https://pith.science/api/pith-number/7A6QJASW575CGSXTZTF7MZFN2H/events.json","paper":"https://pith.science/paper/7A6QJASW"},"agent_actions":{"view_html":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H","download_json":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H.json","view_paper":"https://pith.science/paper/7A6QJASW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11128&json=true","fetch_graph":"https://pith.science/api/pith-number/7A6QJASW575CGSXTZTF7MZFN2H/graph.json","fetch_events":"https://pith.science/api/pith-number/7A6QJASW575CGSXTZTF7MZFN2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H/action/storage_attestation","attest_author":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H/action/author_attestation","sign_citation":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H/action/citation_signature","submit_replication":"https://pith.science/pith/7A6QJASW575CGSXTZTF7MZFN2H/action/replication_record"}},"created_at":"2026-07-05T10:50:41.155533+00:00","updated_at":"2026-07-05T10:50:41.155533+00:00"}