{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DKUZ4PAJPKLRJWSZXUNZOKC25T","short_pith_number":"pith:DKUZ4PAJ","schema_version":"1.0","canonical_sha256":"1aa99e3c097a9714da59bd1b97285aeceb36edde14c519e5959b69e2d40965f2","source":{"kind":"arxiv","id":"1711.04161","version":7},"attestation_state":"computed","paper":{"title":"End-to-end Video-level Representation Learning for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiagang Zhu, Wei Zou, Zheng Zhu","submitted_at":"2017-11-11T15:52:19Z","abstract_excerpt":"From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial observation training, or without end-to-end learning, or restricted to single temporal scale modeling and so on. In this paper, we build upon two-stream ConvNets and propose Deep networks with Temporal Pyramid Pooling (DTPP), an end-to-end video-level representation learning approach, to address these problems. Specifically, at first, RGB images and optical "},"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":"1711.04161","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-11T15:52:19Z","cross_cats_sorted":[],"title_canon_sha256":"3af17218c9118d58a6d25d179954ea6aa90621fe7e2aa957858573a6e63055ae","abstract_canon_sha256":"c1e953bf6ec206c7189f78b3cbbfcf806878302c07d5da1d942b83437bd6d0e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:54.148012Z","signature_b64":"2ZCZBDNQ92c5GPjsXCAsDqYEy28356Sgdwwd779iGr2QplA3RIOcCcorMU/FGZRl2U8ySZbKMfeRtyILT4QMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aa99e3c097a9714da59bd1b97285aeceb36edde14c519e5959b69e2d40965f2","last_reissued_at":"2026-05-18T00:17:54.147377Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:54.147377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Video-level Representation Learning for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiagang Zhu, Wei Zou, Zheng Zhu","submitted_at":"2017-11-11T15:52:19Z","abstract_excerpt":"From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial observation training, or without end-to-end learning, or restricted to single temporal scale modeling and so on. In this paper, we build upon two-stream ConvNets and propose Deep networks with Temporal Pyramid Pooling (DTPP), an end-to-end video-level representation learning approach, to address these problems. Specifically, at first, RGB images and optical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04161","kind":"arxiv","version":7},"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":"1711.04161","created_at":"2026-05-18T00:17:54.147492+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04161v7","created_at":"2026-05-18T00:17:54.147492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04161","created_at":"2026-05-18T00:17:54.147492+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKUZ4PAJPKLR","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKUZ4PAJPKLRJWSZ","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKUZ4PAJ","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/DKUZ4PAJPKLRJWSZXUNZOKC25T","json":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T.json","graph_json":"https://pith.science/api/pith-number/DKUZ4PAJPKLRJWSZXUNZOKC25T/graph.json","events_json":"https://pith.science/api/pith-number/DKUZ4PAJPKLRJWSZXUNZOKC25T/events.json","paper":"https://pith.science/paper/DKUZ4PAJ"},"agent_actions":{"view_html":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T","download_json":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T.json","view_paper":"https://pith.science/paper/DKUZ4PAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04161&json=true","fetch_graph":"https://pith.science/api/pith-number/DKUZ4PAJPKLRJWSZXUNZOKC25T/graph.json","fetch_events":"https://pith.science/api/pith-number/DKUZ4PAJPKLRJWSZXUNZOKC25T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/action/storage_attestation","attest_author":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/action/author_attestation","sign_citation":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/action/citation_signature","submit_replication":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/action/replication_record"}},"created_at":"2026-05-18T00:17:54.147492+00:00","updated_at":"2026-05-18T00:17:54.147492+00:00"}