{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:SB3OLP2KSLI2MXVI4PQU6YNPNL","short_pith_number":"pith:SB3OLP2K","schema_version":"1.0","canonical_sha256":"9076e5bf4a92d1a65ea8e3e14f61af6af838862684deb735cb9fd8a9cc10aaa2","source":{"kind":"arxiv","id":"1405.7545","version":1},"attestation_state":"computed","paper":{"title":"Feature sampling and partitioning for visual vocabulary generation on large action classification datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Cuzzolin, Michael Sapienza, Philip H.S. Torr","submitted_at":"2014-05-29T13:09:52Z","abstract_excerpt":"The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a bag-of-visual-words pipeline in which space-time features are aggregated globally to form a histogram. The strategies chosen to sample features and construct a visual vocabulary are critical to performance, in fact often dominating performance. In this work we provide a critical evaluation of various approaches to building a vocabulary and show that good practises "},"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":"1405.7545","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-29T13:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"2954700853f2546f22613391be3155a60520b1ba7e005f0e9e42ff3a16ad33b1","abstract_canon_sha256":"42fa726283ce76e3bd1abec55fe9a2cdae5a49ab0d1cab0aed55edbb59f8a846"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:51.001823Z","signature_b64":"5f+Sk3wc/3+1fmtLkHU4M9x0VyZu9/wjEKGJExELAzlnnKyUAxDscRVm8/FMQy2W1yUewAHadLk1MUwP7i9MCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9076e5bf4a92d1a65ea8e3e14f61af6af838862684deb735cb9fd8a9cc10aaa2","last_reissued_at":"2026-05-18T02:50:51.001366Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:51.001366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature sampling and partitioning for visual vocabulary generation on large action classification datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Cuzzolin, Michael Sapienza, Philip H.S. Torr","submitted_at":"2014-05-29T13:09:52Z","abstract_excerpt":"The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a bag-of-visual-words pipeline in which space-time features are aggregated globally to form a histogram. The strategies chosen to sample features and construct a visual vocabulary are critical to performance, in fact often dominating performance. In this work we provide a critical evaluation of various approaches to building a vocabulary and show that good practises "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.7545","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":"1405.7545","created_at":"2026-05-18T02:50:51.001432+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.7545v1","created_at":"2026-05-18T02:50:51.001432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.7545","created_at":"2026-05-18T02:50:51.001432+00:00"},{"alias_kind":"pith_short_12","alias_value":"SB3OLP2KSLI2","created_at":"2026-05-18T12:28:49.207871+00:00"},{"alias_kind":"pith_short_16","alias_value":"SB3OLP2KSLI2MXVI","created_at":"2026-05-18T12:28:49.207871+00:00"},{"alias_kind":"pith_short_8","alias_value":"SB3OLP2K","created_at":"2026-05-18T12:28:49.207871+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/SB3OLP2KSLI2MXVI4PQU6YNPNL","json":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL.json","graph_json":"https://pith.science/api/pith-number/SB3OLP2KSLI2MXVI4PQU6YNPNL/graph.json","events_json":"https://pith.science/api/pith-number/SB3OLP2KSLI2MXVI4PQU6YNPNL/events.json","paper":"https://pith.science/paper/SB3OLP2K"},"agent_actions":{"view_html":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL","download_json":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL.json","view_paper":"https://pith.science/paper/SB3OLP2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.7545&json=true","fetch_graph":"https://pith.science/api/pith-number/SB3OLP2KSLI2MXVI4PQU6YNPNL/graph.json","fetch_events":"https://pith.science/api/pith-number/SB3OLP2KSLI2MXVI4PQU6YNPNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL/action/storage_attestation","attest_author":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL/action/author_attestation","sign_citation":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL/action/citation_signature","submit_replication":"https://pith.science/pith/SB3OLP2KSLI2MXVI4PQU6YNPNL/action/replication_record"}},"created_at":"2026-05-18T02:50:51.001432+00:00","updated_at":"2026-05-18T02:50:51.001432+00:00"}