{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GH6XHRFVM3KPC676UHMZOGNNKB","short_pith_number":"pith:GH6XHRFV","schema_version":"1.0","canonical_sha256":"31fd73c4b566d4f17bfea1d99719ad5052ea117af286feb4cf1e60343e8abd84","source":{"kind":"arxiv","id":"1809.04096","version":1},"attestation_state":"computed","paper":{"title":"Parallel Separable 3D Convolution for Video and Volumetric Data Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donglai Wei, Felix Gonda, Hanspeter Pfister, Toufiq Parag","submitted_at":"2018-09-11T18:15:20Z","abstract_excerpt":"For video and volumetric data understanding, 3D convolution layers are widely used in deep learning, however, at the cost of increasing computation and training time. Recent works seek to replace the 3D convolution layer with convolution blocks, e.g. structured combinations of 2D and 1D convolution layers. In this paper, we propose a novel convolution block, Parallel Separable 3D Convolution (PmSCn), which applies m parallel streams of n 2D and one 1D convolution layers along different dimensions. We first mathematically justify the need of parallel streams (Pm) to replace a single 3D convolut"},"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":"1809.04096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T18:15:20Z","cross_cats_sorted":[],"title_canon_sha256":"52c3d016ed6138baee29401c080da30f09258d497ba6711f599e8185302f5087","abstract_canon_sha256":"72e17a2a73e4efa0ef85279b990719b607e8628a690d19707db016defc6a53aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:55.529632Z","signature_b64":"Eq1w/tkj6wQXkVLuAqCazWplwAYmeeRrOCD3ujxzWBRuzej/fvwACcL/VST8IUHKabReZk8OiXWnp9cg/s48Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31fd73c4b566d4f17bfea1d99719ad5052ea117af286feb4cf1e60343e8abd84","last_reissued_at":"2026-05-18T00:05:55.528913Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:55.528913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Separable 3D Convolution for Video and Volumetric Data Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donglai Wei, Felix Gonda, Hanspeter Pfister, Toufiq Parag","submitted_at":"2018-09-11T18:15:20Z","abstract_excerpt":"For video and volumetric data understanding, 3D convolution layers are widely used in deep learning, however, at the cost of increasing computation and training time. Recent works seek to replace the 3D convolution layer with convolution blocks, e.g. structured combinations of 2D and 1D convolution layers. In this paper, we propose a novel convolution block, Parallel Separable 3D Convolution (PmSCn), which applies m parallel streams of n 2D and one 1D convolution layers along different dimensions. We first mathematically justify the need of parallel streams (Pm) to replace a single 3D convolut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04096","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":"1809.04096","created_at":"2026-05-18T00:05:55.529031+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04096v1","created_at":"2026-05-18T00:05:55.529031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04096","created_at":"2026-05-18T00:05:55.529031+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH6XHRFVM3KP","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH6XHRFVM3KPC676","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH6XHRFV","created_at":"2026-05-18T12:32:25.280505+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/GH6XHRFVM3KPC676UHMZOGNNKB","json":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB.json","graph_json":"https://pith.science/api/pith-number/GH6XHRFVM3KPC676UHMZOGNNKB/graph.json","events_json":"https://pith.science/api/pith-number/GH6XHRFVM3KPC676UHMZOGNNKB/events.json","paper":"https://pith.science/paper/GH6XHRFV"},"agent_actions":{"view_html":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB","download_json":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB.json","view_paper":"https://pith.science/paper/GH6XHRFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04096&json=true","fetch_graph":"https://pith.science/api/pith-number/GH6XHRFVM3KPC676UHMZOGNNKB/graph.json","fetch_events":"https://pith.science/api/pith-number/GH6XHRFVM3KPC676UHMZOGNNKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB/action/storage_attestation","attest_author":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB/action/author_attestation","sign_citation":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB/action/citation_signature","submit_replication":"https://pith.science/pith/GH6XHRFVM3KPC676UHMZOGNNKB/action/replication_record"}},"created_at":"2026-05-18T00:05:55.529031+00:00","updated_at":"2026-05-18T00:05:55.529031+00:00"}