{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TJH4EIWJJ7TR3VIGVBNJAT5QQU","short_pith_number":"pith:TJH4EIWJ","schema_version":"1.0","canonical_sha256":"9a4fc222c94fe71dd506a85a904fb0850f9c7165b1c5a2786a5fd8f39cea6eaf","source":{"kind":"arxiv","id":"1803.06962","version":1},"attestation_state":"computed","paper":{"title":"Featureless: Bypassing feature extraction in action categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnold W. M. Smeulders, Jan C. van Gemert, Pascal S. Mettes, Silvia L. Pintea","submitted_at":"2018-03-19T14:47:09Z","abstract_excerpt":"This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit of such an approach is that at the same computational expense it can predict 2 D video representations as well as 3 D ones, based on motion. The proposed model relies on discriminative Waldboost, which we enhance to a multiclass formulation for the purpo"},"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":"1803.06962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-19T14:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"b916c396a091e21ada75d8ce600d3e4b29c0ca6eb579bf45bbc30ce3ea13aef6","abstract_canon_sha256":"b23d3f68791da6a07bae3a58415882306e16a33092c51b1cc5583a17cf10c0d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:40.745998Z","signature_b64":"fjPRGh66pQQzzh+rFLjVFxd/UzMi1NXMQQA376BPuj0gPp5d2c9YJM6SU4P+YQA1g2bPcO9eqnobzTVpxaHhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4fc222c94fe71dd506a85a904fb0850f9c7165b1c5a2786a5fd8f39cea6eaf","last_reissued_at":"2026-05-18T00:20:40.745235Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:40.745235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Featureless: Bypassing feature extraction in action categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnold W. M. Smeulders, Jan C. van Gemert, Pascal S. Mettes, Silvia L. Pintea","submitted_at":"2018-03-19T14:47:09Z","abstract_excerpt":"This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit of such an approach is that at the same computational expense it can predict 2 D video representations as well as 3 D ones, based on motion. The proposed model relies on discriminative Waldboost, which we enhance to a multiclass formulation for the purpo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06962","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":"1803.06962","created_at":"2026-05-18T00:20:40.745375+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06962v1","created_at":"2026-05-18T00:20:40.745375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06962","created_at":"2026-05-18T00:20:40.745375+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJH4EIWJJ7TR","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJH4EIWJJ7TR3VIG","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJH4EIWJ","created_at":"2026-05-18T12:32:53.628368+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/TJH4EIWJJ7TR3VIGVBNJAT5QQU","json":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU.json","graph_json":"https://pith.science/api/pith-number/TJH4EIWJJ7TR3VIGVBNJAT5QQU/graph.json","events_json":"https://pith.science/api/pith-number/TJH4EIWJJ7TR3VIGVBNJAT5QQU/events.json","paper":"https://pith.science/paper/TJH4EIWJ"},"agent_actions":{"view_html":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU","download_json":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU.json","view_paper":"https://pith.science/paper/TJH4EIWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06962&json=true","fetch_graph":"https://pith.science/api/pith-number/TJH4EIWJJ7TR3VIGVBNJAT5QQU/graph.json","fetch_events":"https://pith.science/api/pith-number/TJH4EIWJJ7TR3VIGVBNJAT5QQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU/action/storage_attestation","attest_author":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU/action/author_attestation","sign_citation":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU/action/citation_signature","submit_replication":"https://pith.science/pith/TJH4EIWJJ7TR3VIGVBNJAT5QQU/action/replication_record"}},"created_at":"2026-05-18T00:20:40.745375+00:00","updated_at":"2026-05-18T00:20:40.745375+00:00"}