{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DKUZ4PAJPKLRJWSZXUNZOKC25T","short_pith_number":"pith:DKUZ4PAJ","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"},"canonical_sha256":"1aa99e3c097a9714da59bd1b97285aeceb36edde14c519e5959b69e2d40965f2","source":{"kind":"arxiv","id":"1711.04161","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04161","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04161v7","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04161","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"DKUZ4PAJPKLR","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DKUZ4PAJPKLRJWSZ","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DKUZ4PAJ","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DKUZ4PAJPKLRJWSZXUNZOKC25T","target":"record","payload":{"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"},"canonical_sha256":"1aa99e3c097a9714da59bd1b97285aeceb36edde14c519e5959b69e2d40965f2","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"},"source_kind":"arxiv","source_id":"1711.04161","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWwAnNDjabUrTpnSMnKuhyboII0ir445eqZXlnd0t1Mgoh7VD2nGVBYVUJuVrygCaK6eNmWlZfBP/aQSq6HQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T04:24:31.044438Z"},"content_sha256":"f1e7e20608d9181a7379fb5467481a7d4f7c9063280de3ec27a37d9b7e517c68","schema_version":"1.0","event_id":"sha256:f1e7e20608d9181a7379fb5467481a7d4f7c9063280de3ec27a37d9b7e517c68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DKUZ4PAJPKLRJWSZXUNZOKC25T","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6aYIXArSmlYmmMO/ulAPC0nBGFN2DjogUBQIrHSqJYvAyakJrFN+weMRy9kwL5ch2Kh5EpXZxjKCQbUYml1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T04:24:31.045008Z"},"content_sha256":"1279c46e501f97cd6e444d15d800f72bb161c90b8ac95d5a1c516e596c90a4ed","schema_version":"1.0","event_id":"sha256:1279c46e501f97cd6e444d15d800f72bb161c90b8ac95d5a1c516e596c90a4ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/bundle.json","state_url":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T04:24:31Z","links":{"resolver":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T","bundle":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/bundle.json","state":"https://pith.science/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKUZ4PAJPKLRJWSZXUNZOKC25T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DKUZ4PAJPKLRJWSZXUNZOKC25T","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1e953bf6ec206c7189f78b3cbbfcf806878302c07d5da1d942b83437bd6d0e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-11T15:52:19Z","title_canon_sha256":"3af17218c9118d58a6d25d179954ea6aa90621fe7e2aa957858573a6e63055ae"},"schema_version":"1.0","source":{"id":"1711.04161","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04161","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04161v7","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04161","created_at":"2026-05-18T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"DKUZ4PAJPKLR","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DKUZ4PAJPKLRJWSZ","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DKUZ4PAJ","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:1279c46e501f97cd6e444d15d800f72bb161c90b8ac95d5a1c516e596c90a4ed","target":"graph","created_at":"2026-05-18T00:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Jiagang Zhu, Wei Zou, Zheng Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-11T15:52:19Z","title":"End-to-end Video-level Representation Learning for Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04161","kind":"arxiv","version":7},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f1e7e20608d9181a7379fb5467481a7d4f7c9063280de3ec27a37d9b7e517c68","target":"record","created_at":"2026-05-18T00:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c1e953bf6ec206c7189f78b3cbbfcf806878302c07d5da1d942b83437bd6d0e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-11T15:52:19Z","title_canon_sha256":"3af17218c9118d58a6d25d179954ea6aa90621fe7e2aa957858573a6e63055ae"},"schema_version":"1.0","source":{"id":"1711.04161","kind":"arxiv","version":7}},"canonical_sha256":"1aa99e3c097a9714da59bd1b97285aeceb36edde14c519e5959b69e2d40965f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aa99e3c097a9714da59bd1b97285aeceb36edde14c519e5959b69e2d40965f2","first_computed_at":"2026-05-18T00:17:54.147377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:54.147377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2ZCZBDNQ92c5GPjsXCAsDqYEy28356Sgdwwd779iGr2QplA3RIOcCcorMU/FGZRl2U8ySZbKMfeRtyILT4QMBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:54.148012Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.04161","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1e7e20608d9181a7379fb5467481a7d4f7c9063280de3ec27a37d9b7e517c68","sha256:1279c46e501f97cd6e444d15d800f72bb161c90b8ac95d5a1c516e596c90a4ed"],"state_sha256":"0dc43b4f0aa9cd23fc6ec9cf2c6827701c18813da51addd2903308a4ed6b6c5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPpfNnDOo+wSQVCFGUaZSkYSKVu+rAHcFVxLf58K95TuQWVT7aUTHOuFQpCUt/ksivre+qPBlL5xArQ2GvH8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T04:24:31.046725Z","bundle_sha256":"16f1f296740b9ce507045c4330aa86b06eb41267bd576f769e2a326f565dc5f9"}}