{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PZ4K57KX3HDI36V6G3MHOVW73H","short_pith_number":"pith:PZ4K57KX","schema_version":"1.0","canonical_sha256":"7e78aefd57d9c68dfabe36d87756dfd9e331d74c70947869b2a4dfcd44f44fb5","source":{"kind":"arxiv","id":"1806.07754","version":3},"attestation_state":"computed","paper":{"title":"Spatio-Temporal Channel Correlation Networks for Action Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Diba, Juergen Gall, Luc Van Gool, M.Mahdi Arzani, Mohsen Fayyaz, Rahman Yousefzadeh, Vivek Sharma","submitted_at":"2018-06-19T12:43:40Z","abstract_excerpt":"The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models correlations between channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block 'Spatio-Temporal Channel Correlation' (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improved the perfo"},"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":"1806.07754","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-19T12:43:40Z","cross_cats_sorted":[],"title_canon_sha256":"5cfe2baceba20db692ff5b0c074b51f92684ab8d390a54436703bb8f95fbdfe7","abstract_canon_sha256":"b32028ef64b16ab1a88cc1f953bc2f5e7349a83ed010299aadac7cd2e04a487c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:34.333223Z","signature_b64":"0oOLi4nW3A2SlW9W+NQipH2xhycW76IFk0Ee5V9zVg/imCCuQmpIPjFbQL00fTsOTvZAqOTijY9c/rBmHvVlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e78aefd57d9c68dfabe36d87756dfd9e331d74c70947869b2a4dfcd44f44fb5","last_reissued_at":"2026-05-17T23:54:34.332724Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:34.332724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatio-Temporal Channel Correlation Networks for Action Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Diba, Juergen Gall, Luc Van Gool, M.Mahdi Arzani, Mohsen Fayyaz, Rahman Yousefzadeh, Vivek Sharma","submitted_at":"2018-06-19T12:43:40Z","abstract_excerpt":"The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models correlations between channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block 'Spatio-Temporal Channel Correlation' (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improved the perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07754","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":""},"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":"1806.07754","created_at":"2026-05-17T23:54:34.332800+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.07754v3","created_at":"2026-05-17T23:54:34.332800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07754","created_at":"2026-05-17T23:54:34.332800+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZ4K57KX3HDI","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZ4K57KX3HDI36V6","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZ4K57KX","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04632","citing_title":"Video Action Recognition Via Neural Architecture Searching","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H","json":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H.json","graph_json":"https://pith.science/api/pith-number/PZ4K57KX3HDI36V6G3MHOVW73H/graph.json","events_json":"https://pith.science/api/pith-number/PZ4K57KX3HDI36V6G3MHOVW73H/events.json","paper":"https://pith.science/paper/PZ4K57KX"},"agent_actions":{"view_html":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H","download_json":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H.json","view_paper":"https://pith.science/paper/PZ4K57KX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.07754&json=true","fetch_graph":"https://pith.science/api/pith-number/PZ4K57KX3HDI36V6G3MHOVW73H/graph.json","fetch_events":"https://pith.science/api/pith-number/PZ4K57KX3HDI36V6G3MHOVW73H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H/action/storage_attestation","attest_author":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H/action/author_attestation","sign_citation":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H/action/citation_signature","submit_replication":"https://pith.science/pith/PZ4K57KX3HDI36V6G3MHOVW73H/action/replication_record"}},"created_at":"2026-05-17T23:54:34.332800+00:00","updated_at":"2026-05-17T23:54:34.332800+00:00"}