{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VEM2PDUM42CRX43FQE5BEYMN44","short_pith_number":"pith:VEM2PDUM","schema_version":"1.0","canonical_sha256":"a919a78e8ce6851bf365813a12618de70d11debb22647db5dd09def57265054a","source":{"kind":"arxiv","id":"1707.09468","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Activity Recognition with Verb Attribute Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Rowan Zellers, Yejin Choi","submitted_at":"2017-07-29T06:05:52Z","abstract_excerpt":"In this paper, we investigate large-scale zero-shot activity recognition by modeling the visual and linguistic attributes of action verbs. For example, the verb \"salute\" has several properties, such as being a light movement, a social act, and short in duration. We use these attributes as the internal mapping between visual and textual representations to reason about a previously unseen action. In contrast to much prior work that assumes access to gold standard attributes for zero-shot classes and focuses primarily on object attributes, our model uniquely learns to infer action attributes from"},"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":"1707.09468","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-29T06:05:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d8332f338c8fe81f31c23e8c2816a7e187ba6bf1d2cfbb15a10c04e4357f82e5","abstract_canon_sha256":"33372d93453761d5be77d8530fe423c5c301aab96dcebd607b48be56d4cbdd2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:08.390630Z","signature_b64":"69X1j1YbryHAsvhcfM7JMNK9yOxuMkbNwfCxlBCjAJM1ESinHt6FLsmEAa+45QnmZuAMZHcZhATL8VGxKGEcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a919a78e8ce6851bf365813a12618de70d11debb22647db5dd09def57265054a","last_reissued_at":"2026-05-18T00:36:08.390003Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:08.390003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Activity Recognition with Verb Attribute Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Rowan Zellers, Yejin Choi","submitted_at":"2017-07-29T06:05:52Z","abstract_excerpt":"In this paper, we investigate large-scale zero-shot activity recognition by modeling the visual and linguistic attributes of action verbs. For example, the verb \"salute\" has several properties, such as being a light movement, a social act, and short in duration. We use these attributes as the internal mapping between visual and textual representations to reason about a previously unseen action. In contrast to much prior work that assumes access to gold standard attributes for zero-shot classes and focuses primarily on object attributes, our model uniquely learns to infer action attributes from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09468","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":"1707.09468","created_at":"2026-05-18T00:36:08.390100+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09468v2","created_at":"2026-05-18T00:36:08.390100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09468","created_at":"2026-05-18T00:36:08.390100+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEM2PDUM42CR","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEM2PDUM42CRX43F","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEM2PDUM","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06803","citing_title":"Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44","json":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44.json","graph_json":"https://pith.science/api/pith-number/VEM2PDUM42CRX43FQE5BEYMN44/graph.json","events_json":"https://pith.science/api/pith-number/VEM2PDUM42CRX43FQE5BEYMN44/events.json","paper":"https://pith.science/paper/VEM2PDUM"},"agent_actions":{"view_html":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44","download_json":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44.json","view_paper":"https://pith.science/paper/VEM2PDUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09468&json=true","fetch_graph":"https://pith.science/api/pith-number/VEM2PDUM42CRX43FQE5BEYMN44/graph.json","fetch_events":"https://pith.science/api/pith-number/VEM2PDUM42CRX43FQE5BEYMN44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44/action/storage_attestation","attest_author":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44/action/author_attestation","sign_citation":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44/action/citation_signature","submit_replication":"https://pith.science/pith/VEM2PDUM42CRX43FQE5BEYMN44/action/replication_record"}},"created_at":"2026-05-18T00:36:08.390100+00:00","updated_at":"2026-05-18T00:36:08.390100+00:00"}