{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CMWYYOYRRPQTMMNWPBSZSR3LHM","short_pith_number":"pith:CMWYYOYR","schema_version":"1.0","canonical_sha256":"132d8c3b118be13631b6786599476b3b1ee7d0c4201853ebd4af6434a6c00dc9","source":{"kind":"arxiv","id":"1712.04851","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Sun, Jonathan Huang, Kevin Murphy, Saining Xie, Zhuowen Tu","submitted_at":"2017-12-13T16:40:55Z","abstract_excerpt":"Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including spatial (image) feature representation, temporal information representation, and model/computation complexity. It was recently shown by Carreira and Zisserman that 3D CNNs, inflated from 2D networks and pretrained on ImageNet, could be a promising way for spatial and temporal representation learning. However, as for model/computation complexity, 3D CNNs are much "},"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":"1712.04851","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-13T16:40:55Z","cross_cats_sorted":[],"title_canon_sha256":"5f047f4b137f23fe56ae9cc3471efcea8567f10919d36af824f82cb8d10b7aa7","abstract_canon_sha256":"771ba59ab0a1d0a52326a1fa88f4f93d138f9ead43cdeca24a2e4dbf698e41e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:41.915209Z","signature_b64":"e4bkCWusnBgscEfJpZo9R8ANQhqVLDF3SHMyaEP7SfAHKapk4TqzvLHx8weeMpSSaxoT4gp09K/r5q4VIPtoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"132d8c3b118be13631b6786599476b3b1ee7d0c4201853ebd4af6434a6c00dc9","last_reissued_at":"2026-05-18T00:09:41.914659Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:41.914659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Sun, Jonathan Huang, Kevin Murphy, Saining Xie, Zhuowen Tu","submitted_at":"2017-12-13T16:40:55Z","abstract_excerpt":"Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including spatial (image) feature representation, temporal information representation, and model/computation complexity. It was recently shown by Carreira and Zisserman that 3D CNNs, inflated from 2D networks and pretrained on ImageNet, could be a promising way for spatial and temporal representation learning. However, as for model/computation complexity, 3D CNNs are much "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04851","kind":"arxiv","version":2},"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":"1712.04851","created_at":"2026-05-18T00:09:41.914741+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.04851v2","created_at":"2026-05-18T00:09:41.914741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04851","created_at":"2026-05-18T00:09:41.914741+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMWYYOYRRPQT","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMWYYOYRRPQTMMNW","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMWYYOYR","created_at":"2026-05-18T12:31:10.602751+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/CMWYYOYRRPQTMMNWPBSZSR3LHM","json":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM.json","graph_json":"https://pith.science/api/pith-number/CMWYYOYRRPQTMMNWPBSZSR3LHM/graph.json","events_json":"https://pith.science/api/pith-number/CMWYYOYRRPQTMMNWPBSZSR3LHM/events.json","paper":"https://pith.science/paper/CMWYYOYR"},"agent_actions":{"view_html":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM","download_json":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM.json","view_paper":"https://pith.science/paper/CMWYYOYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.04851&json=true","fetch_graph":"https://pith.science/api/pith-number/CMWYYOYRRPQTMMNWPBSZSR3LHM/graph.json","fetch_events":"https://pith.science/api/pith-number/CMWYYOYRRPQTMMNWPBSZSR3LHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM/action/storage_attestation","attest_author":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM/action/author_attestation","sign_citation":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM/action/citation_signature","submit_replication":"https://pith.science/pith/CMWYYOYRRPQTMMNWPBSZSR3LHM/action/replication_record"}},"created_at":"2026-05-18T00:09:41.914741+00:00","updated_at":"2026-05-18T00:09:41.914741+00:00"}