{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EUCKOERWMVH43WSPIP6VOL2PG6","short_pith_number":"pith:EUCKOERW","schema_version":"1.0","canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","source":{"kind":"arxiv","id":"1707.04555","version":1},"attestation_state":"computed","paper":{"title":"Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Fu Li, Jie Zhou, Shilei Wen, Xiang Long, Xiao Liu, Yandong Li, Yunlong Bian, Zhichao Li","submitted_at":"2017-07-14T16:11:14Z","abstract_excerpt":"This paper describes our solution for the video recognition task of the Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd place. Because the challenge provides pre-extracted visual and audio features instead of the raw videos, we mainly investigate various temporal modeling approaches to aggregate the frame-level features for multi-label video recognition. Our system contains three major components: two-stream sequence model, fast-forward sequence model and temporal residual neural networks. Experiment results on the challenging Youtube-8M dataset demonstrate that o"},"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":"1707.04555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T16:11:14Z","cross_cats_sorted":[],"title_canon_sha256":"3ceeb3dbbd79d6af02895dde949c1ec99e16012897624c9e5d9002e37c1146b6","abstract_canon_sha256":"2e60d355ecb9775bcfcc550d5c132658a0d27eee77ee2c4601d3f8f043034342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:17.754476Z","signature_b64":"oOHWWvhOvMGPmm2ty3enGgDedw+IjgY1JZksGl4ZWd54qzh/0HT66Py+MHWaMShkr++rvzm7Bm/+WptOG8qwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","last_reissued_at":"2026-05-18T00:40:17.753665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:17.753665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Fu Li, Jie Zhou, Shilei Wen, Xiang Long, Xiao Liu, Yandong Li, Yunlong Bian, Zhichao Li","submitted_at":"2017-07-14T16:11:14Z","abstract_excerpt":"This paper describes our solution for the video recognition task of the Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd place. Because the challenge provides pre-extracted visual and audio features instead of the raw videos, we mainly investigate various temporal modeling approaches to aggregate the frame-level features for multi-label video recognition. Our system contains three major components: two-stream sequence model, fast-forward sequence model and temporal residual neural networks. Experiment results on the challenging Youtube-8M dataset demonstrate that o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04555","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":"1707.04555","created_at":"2026-05-18T00:40:17.753798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.04555v1","created_at":"2026-05-18T00:40:17.753798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04555","created_at":"2026-05-18T00:40:17.753798+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUCKOERWMVH4","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUCKOERWMVH43WSP","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUCKOERW","created_at":"2026-05-18T12:31:12.930513+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/EUCKOERWMVH43WSPIP6VOL2PG6","json":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6.json","graph_json":"https://pith.science/api/pith-number/EUCKOERWMVH43WSPIP6VOL2PG6/graph.json","events_json":"https://pith.science/api/pith-number/EUCKOERWMVH43WSPIP6VOL2PG6/events.json","paper":"https://pith.science/paper/EUCKOERW"},"agent_actions":{"view_html":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6","download_json":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6.json","view_paper":"https://pith.science/paper/EUCKOERW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.04555&json=true","fetch_graph":"https://pith.science/api/pith-number/EUCKOERWMVH43WSPIP6VOL2PG6/graph.json","fetch_events":"https://pith.science/api/pith-number/EUCKOERWMVH43WSPIP6VOL2PG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/action/storage_attestation","attest_author":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/action/author_attestation","sign_citation":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/action/citation_signature","submit_replication":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/action/replication_record"}},"created_at":"2026-05-18T00:40:17.753798+00:00","updated_at":"2026-05-18T00:40:17.753798+00:00"}