{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JH4CHS4DZPB34LJIM6ESGFLQ4B","short_pith_number":"pith:JH4CHS4D","schema_version":"1.0","canonical_sha256":"49f823cb83cbc3be2d286789231570e07f4315765f0f7d00abd7b64e08d4c416","source":{"kind":"arxiv","id":"2110.13479","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlo Bretti, Pascal Mettes","submitted_at":"2021-10-26T08:23:14Z","abstract_excerpt":"This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the image domain by recognizing objects in videos using pre-trained networks, followed by a semantic matching between objects and actions. Where objects provide a local view on the content in videos, in this work we also seek to include a global view of the scene in which actions occur. We find that scenes on their own are also capable of recognizing unseen actions,"},"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":"2110.13479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T08:23:14Z","cross_cats_sorted":[],"title_canon_sha256":"224cad3ad439065a9dd475cf29793304f23148137025a203643023a3a1e941ce","abstract_canon_sha256":"e9ced69f736d836730305889cf40ea1093a9bdb9914fec66be297637adcf4b3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:39.332545Z","signature_b64":"7HcU71+/AwVMUCBtFFJajqqiHSGaI+HDbTwHLh2qmYwJc70OqnasGBKReGUbBtrcFXz3sRBMt5LCri684Nq9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49f823cb83cbc3be2d286789231570e07f4315765f0f7d00abd7b64e08d4c416","last_reissued_at":"2026-07-05T03:25:39.332173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:39.332173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlo Bretti, Pascal Mettes","submitted_at":"2021-10-26T08:23:14Z","abstract_excerpt":"This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the image domain by recognizing objects in videos using pre-trained networks, followed by a semantic matching between objects and actions. Where objects provide a local view on the content in videos, in this work we also seek to include a global view of the scene in which actions occur. We find that scenes on their own are also capable of recognizing unseen actions,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13479","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.13479/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.13479","created_at":"2026-07-05T03:25:39.332229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13479v1","created_at":"2026-07-05T03:25:39.332229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13479","created_at":"2026-07-05T03:25:39.332229+00:00"},{"alias_kind":"pith_short_12","alias_value":"JH4CHS4DZPB3","created_at":"2026-07-05T03:25:39.332229+00:00"},{"alias_kind":"pith_short_16","alias_value":"JH4CHS4DZPB34LJI","created_at":"2026-07-05T03:25:39.332229+00:00"},{"alias_kind":"pith_short_8","alias_value":"JH4CHS4D","created_at":"2026-07-05T03:25:39.332229+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/JH4CHS4DZPB34LJIM6ESGFLQ4B","json":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B.json","graph_json":"https://pith.science/api/pith-number/JH4CHS4DZPB34LJIM6ESGFLQ4B/graph.json","events_json":"https://pith.science/api/pith-number/JH4CHS4DZPB34LJIM6ESGFLQ4B/events.json","paper":"https://pith.science/paper/JH4CHS4D"},"agent_actions":{"view_html":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B","download_json":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B.json","view_paper":"https://pith.science/paper/JH4CHS4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13479&json=true","fetch_graph":"https://pith.science/api/pith-number/JH4CHS4DZPB34LJIM6ESGFLQ4B/graph.json","fetch_events":"https://pith.science/api/pith-number/JH4CHS4DZPB34LJIM6ESGFLQ4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B/action/storage_attestation","attest_author":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B/action/author_attestation","sign_citation":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B/action/citation_signature","submit_replication":"https://pith.science/pith/JH4CHS4DZPB34LJIM6ESGFLQ4B/action/replication_record"}},"created_at":"2026-07-05T03:25:39.332229+00:00","updated_at":"2026-07-05T03:25:39.332229+00:00"}