{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZZBQTHQA3PCGPGVM5TQLNX2TNN","short_pith_number":"pith:ZZBQTHQA","schema_version":"1.0","canonical_sha256":"ce43099e00dbc4679aacece0b6df536b79b898daa96c7eae2c6e33b22f419fcc","source":{"kind":"arxiv","id":"2203.05928","version":1},"attestation_state":"computed","paper":{"title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shiwen Zhang","submitted_at":"2022-03-11T13:58:05Z","abstract_excerpt":"Temporal Reasoning is one important functionality for vision intelligence. In computer vision research community, temporal reasoning is usually studied in the form of video classification, for which many state-of-the-art Neural Network structures and dataset benchmarks are proposed in recent years, especially 3D CNNs and Kinetics. However, some recent works found that current video classification benchmarks contain strong biases towards static features, thus cannot accurately reflect the temporal modeling ability. New video classification benchmarks aiming to eliminate static biases are propos"},"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":"2203.05928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-11T13:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"ec24c88fd241e4a24d40b420c41956b654b5c92f21f4dcbf5c1bb1aaa54a27e1","abstract_canon_sha256":"4ebc218ae1d7b1a1d691625fa7badeca2378c0ec7af191812bc2a96081d46c08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:11.021367Z","signature_b64":"LOLyORBrd2Zo5LRDhQ09khr+bQ2fgtJhxdAdru7je+W7LbuCqJ0g1h+slH3Djn9NI1ao2ePvwwid1Zyfwf0wDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce43099e00dbc4679aacece0b6df536b79b898daa96c7eae2c6e33b22f419fcc","last_reissued_at":"2026-07-05T04:04:11.021009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:11.021009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shiwen Zhang","submitted_at":"2022-03-11T13:58:05Z","abstract_excerpt":"Temporal Reasoning is one important functionality for vision intelligence. In computer vision research community, temporal reasoning is usually studied in the form of video classification, for which many state-of-the-art Neural Network structures and dataset benchmarks are proposed in recent years, especially 3D CNNs and Kinetics. However, some recent works found that current video classification benchmarks contain strong biases towards static features, thus cannot accurately reflect the temporal modeling ability. New video classification benchmarks aiming to eliminate static biases are propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05928","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/2203.05928/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":"2203.05928","created_at":"2026-07-05T04:04:11.021066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05928v1","created_at":"2026-07-05T04:04:11.021066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05928","created_at":"2026-07-05T04:04:11.021066+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZBQTHQA3PCG","created_at":"2026-07-05T04:04:11.021066+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZBQTHQA3PCGPGVM","created_at":"2026-07-05T04:04:11.021066+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZBQTHQA","created_at":"2026-07-05T04:04:11.021066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14746","citing_title":"Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20709","citing_title":"TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN","json":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN.json","graph_json":"https://pith.science/api/pith-number/ZZBQTHQA3PCGPGVM5TQLNX2TNN/graph.json","events_json":"https://pith.science/api/pith-number/ZZBQTHQA3PCGPGVM5TQLNX2TNN/events.json","paper":"https://pith.science/paper/ZZBQTHQA"},"agent_actions":{"view_html":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN","download_json":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN.json","view_paper":"https://pith.science/paper/ZZBQTHQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05928&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZBQTHQA3PCGPGVM5TQLNX2TNN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZBQTHQA3PCGPGVM5TQLNX2TNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN/action/storage_attestation","attest_author":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN/action/author_attestation","sign_citation":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN/action/citation_signature","submit_replication":"https://pith.science/pith/ZZBQTHQA3PCGPGVM5TQLNX2TNN/action/replication_record"}},"created_at":"2026-07-05T04:04:11.021066+00:00","updated_at":"2026-07-05T04:04:11.021066+00:00"}