{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4DLFVPHOVV7BGIC26753G3AIE7","short_pith_number":"pith:4DLFVPHO","schema_version":"1.0","canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","source":{"kind":"arxiv","id":"1704.06925","version":2},"attestation_state":"computed","paper":{"title":"Second-order Temporal Pooling for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Stephen Gould","submitted_at":"2017-04-23T14:10:55Z","abstract_excerpt":"Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these features. Typically zero-th (max) or the first-order (average) statistics are used. In this paper, we explore the benefits of using second-order statistics. Specifically, we propose a novel end-to-end learnable feature aggregation scheme, dubbed temporal correlation pooling that generates an action descriptor for a video sequence by capturing the similarities betwee"},"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":"1704.06925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T14:10:55Z","cross_cats_sorted":[],"title_canon_sha256":"00fb818ba2d71aed396ca88d6c3386eddc9e606ac73425b2a48545eaeb44552e","abstract_canon_sha256":"c77536661cf19314fbde419b26d392c603067453ef642b989e5b26a3b21d6c62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:48.636407Z","signature_b64":"a10WyB/mgC+F+fpbvN/qAZO6Y3WZPl0WTYLawZqPWFuIEGGJ+UTqocKrg/B4sz5JeYPA+J6vmFM6MWin9uglAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0d65abceead7e13205af7fbb36c0827e4deb8eadd787508841349520995358c","last_reissued_at":"2026-05-18T00:08:48.635726Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:48.635726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Second-order Temporal Pooling for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Stephen Gould","submitted_at":"2017-04-23T14:10:55Z","abstract_excerpt":"Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these features. Typically zero-th (max) or the first-order (average) statistics are used. In this paper, we explore the benefits of using second-order statistics. Specifically, we propose a novel end-to-end learnable feature aggregation scheme, dubbed temporal correlation pooling that generates an action descriptor for a video sequence by capturing the similarities betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06925","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":"1704.06925","created_at":"2026-05-18T00:08:48.635837+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06925v2","created_at":"2026-05-18T00:08:48.635837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06925","created_at":"2026-05-18T00:08:48.635837+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DLFVPHOVV7B","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DLFVPHOVV7BGIC2","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DLFVPHO","created_at":"2026-05-18T12:30:58.224056+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/4DLFVPHOVV7BGIC26753G3AIE7","json":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7.json","graph_json":"https://pith.science/api/pith-number/4DLFVPHOVV7BGIC26753G3AIE7/graph.json","events_json":"https://pith.science/api/pith-number/4DLFVPHOVV7BGIC26753G3AIE7/events.json","paper":"https://pith.science/paper/4DLFVPHO"},"agent_actions":{"view_html":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7","download_json":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7.json","view_paper":"https://pith.science/paper/4DLFVPHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06925&json=true","fetch_graph":"https://pith.science/api/pith-number/4DLFVPHOVV7BGIC26753G3AIE7/graph.json","fetch_events":"https://pith.science/api/pith-number/4DLFVPHOVV7BGIC26753G3AIE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/action/storage_attestation","attest_author":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/action/author_attestation","sign_citation":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/action/citation_signature","submit_replication":"https://pith.science/pith/4DLFVPHOVV7BGIC26753G3AIE7/action/replication_record"}},"created_at":"2026-05-18T00:08:48.635837+00:00","updated_at":"2026-05-18T00:08:48.635837+00:00"}