{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:W6WSCCU5KZUN6S7256RQJQNXA4","short_pith_number":"pith:W6WSCCU5","schema_version":"1.0","canonical_sha256":"b7ad210a9d5668df4bfaefa304c1b70720c25533d7d0f825afd79f8499db86ac","source":{"kind":"arxiv","id":"2012.00317","version":3},"attestation_state":"computed","paper":{"title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyung-Il Kim, Jinyoung Moon, Kimin Yun, Youngwan Lee","submitted_at":"2020-12-01T07:40:06Z","abstract_excerpt":"Video classification researches that have recently attracted attention are the fields of temporal modeling and 3D efficient architecture. However, the temporal modeling methods are not efficient or the 3D efficient architecture is less interested in temporal modeling. For bridging the gap between them, we propose an efficient temporal modeling 3D architecture, called VoV3D, that consists of a temporal one-shot aggregation (T-OSA) module and depthwise factorized component, D(2+1)D. The T-OSA is devised to build a feature hierarchy by aggregating temporal features with different temporal recepti"},"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":"2012.00317","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-01T07:40:06Z","cross_cats_sorted":[],"title_canon_sha256":"3a36ca0141e96667d7a32b9330414d5294e335363094eed5502bcda384d9928b","abstract_canon_sha256":"f4835539a424cabd583ef5a152a3eb87893a80ad3664c445d323f87759e702d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:10.451105Z","signature_b64":"y9IjceE+tKjYbV1qsAjYJEY5BixpnM4nFJ86YmEYSMJu5fBpSd9iRo7kaSJ4lkBXAOmB/CBVq38kDHqthGdUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7ad210a9d5668df4bfaefa304c1b70720c25533d7d0f825afd79f8499db86ac","last_reissued_at":"2026-07-05T02:34:10.450721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:10.450721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyung-Il Kim, Jinyoung Moon, Kimin Yun, Youngwan Lee","submitted_at":"2020-12-01T07:40:06Z","abstract_excerpt":"Video classification researches that have recently attracted attention are the fields of temporal modeling and 3D efficient architecture. However, the temporal modeling methods are not efficient or the 3D efficient architecture is less interested in temporal modeling. For bridging the gap between them, we propose an efficient temporal modeling 3D architecture, called VoV3D, that consists of a temporal one-shot aggregation (T-OSA) module and depthwise factorized component, D(2+1)D. The T-OSA is devised to build a feature hierarchy by aggregating temporal features with different temporal recepti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00317","kind":"arxiv","version":3},"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/2012.00317/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":"2012.00317","created_at":"2026-07-05T02:34:10.450774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00317v3","created_at":"2026-07-05T02:34:10.450774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00317","created_at":"2026-07-05T02:34:10.450774+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6WSCCU5KZUN","created_at":"2026-07-05T02:34:10.450774+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6WSCCU5KZUN6S72","created_at":"2026-07-05T02:34:10.450774+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6WSCCU5","created_at":"2026-07-05T02:34:10.450774+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/W6WSCCU5KZUN6S7256RQJQNXA4","json":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4.json","graph_json":"https://pith.science/api/pith-number/W6WSCCU5KZUN6S7256RQJQNXA4/graph.json","events_json":"https://pith.science/api/pith-number/W6WSCCU5KZUN6S7256RQJQNXA4/events.json","paper":"https://pith.science/paper/W6WSCCU5"},"agent_actions":{"view_html":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4","download_json":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4.json","view_paper":"https://pith.science/paper/W6WSCCU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00317&json=true","fetch_graph":"https://pith.science/api/pith-number/W6WSCCU5KZUN6S7256RQJQNXA4/graph.json","fetch_events":"https://pith.science/api/pith-number/W6WSCCU5KZUN6S7256RQJQNXA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4/action/storage_attestation","attest_author":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4/action/author_attestation","sign_citation":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4/action/citation_signature","submit_replication":"https://pith.science/pith/W6WSCCU5KZUN6S7256RQJQNXA4/action/replication_record"}},"created_at":"2026-07-05T02:34:10.450774+00:00","updated_at":"2026-07-05T02:34:10.450774+00:00"}