{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5QRGCR2XS6CNMJ4AWDQKP7TCIH","short_pith_number":"pith:5QRGCR2X","schema_version":"1.0","canonical_sha256":"ec226147579784d62780b0e0a7fe6241f44d487427ec507484414ef3e0850b9f","source":{"kind":"arxiv","id":"1812.06203","version":1},"attestation_state":"computed","paper":{"title":"TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Joe Yue-Hei Ng, Larry S. Davis, Xiyang Dai","submitted_at":"2018-12-14T23:28:39Z","abstract_excerpt":"We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for capturing spatio-temporal information in videos. Since we do not apply 3D convolutions in each layer but only apply temporal aggregation blocks once after each spatial downsampling layer in the network, we significantly reduce the model complexity. The use of dilated convolutions at different resolutions of the network helps in aggregating multi-scale spatio-tempora"},"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":"1812.06203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-14T23:28:39Z","cross_cats_sorted":[],"title_canon_sha256":"bcfa227d24c7b69e5533983e75adc3d0e45db311a559f9ada5a4a7db5b961125","abstract_canon_sha256":"fd1bc2c51d23894a842c52b2807099cd5756eb1f80e2ee30df2642936f202c73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:12.889236Z","signature_b64":"aRrHy/dRvX3m7j46Z0A/WwBEC1OjxQdyUoVxT4tAK4XRmvGDv+9y4B5IfOYonSVZ8jEVpSKod0k6YGNhFjotAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec226147579784d62780b0e0a7fe6241f44d487427ec507484414ef3e0850b9f","last_reissued_at":"2026-05-17T23:58:12.888750Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:12.888750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Joe Yue-Hei Ng, Larry S. Davis, Xiyang Dai","submitted_at":"2018-12-14T23:28:39Z","abstract_excerpt":"We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for capturing spatio-temporal information in videos. Since we do not apply 3D convolutions in each layer but only apply temporal aggregation blocks once after each spatial downsampling layer in the network, we significantly reduce the model complexity. The use of dilated convolutions at different resolutions of the network helps in aggregating multi-scale spatio-tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06203","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":""},"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":"1812.06203","created_at":"2026-05-17T23:58:12.888816+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.06203v1","created_at":"2026-05-17T23:58:12.888816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06203","created_at":"2026-05-17T23:58:12.888816+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QRGCR2XS6CN","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QRGCR2XS6CNMJ4A","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QRGCR2X","created_at":"2026-05-18T12:32:08.215937+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/5QRGCR2XS6CNMJ4AWDQKP7TCIH","json":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH.json","graph_json":"https://pith.science/api/pith-number/5QRGCR2XS6CNMJ4AWDQKP7TCIH/graph.json","events_json":"https://pith.science/api/pith-number/5QRGCR2XS6CNMJ4AWDQKP7TCIH/events.json","paper":"https://pith.science/paper/5QRGCR2X"},"agent_actions":{"view_html":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH","download_json":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH.json","view_paper":"https://pith.science/paper/5QRGCR2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.06203&json=true","fetch_graph":"https://pith.science/api/pith-number/5QRGCR2XS6CNMJ4AWDQKP7TCIH/graph.json","fetch_events":"https://pith.science/api/pith-number/5QRGCR2XS6CNMJ4AWDQKP7TCIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH/action/storage_attestation","attest_author":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH/action/author_attestation","sign_citation":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH/action/citation_signature","submit_replication":"https://pith.science/pith/5QRGCR2XS6CNMJ4AWDQKP7TCIH/action/replication_record"}},"created_at":"2026-05-17T23:58:12.888816+00:00","updated_at":"2026-05-17T23:58:12.888816+00:00"}