{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V2KQFFC3UHTSKD3QZPEO63G6BV","short_pith_number":"pith:V2KQFFC3","schema_version":"1.0","canonical_sha256":"ae9502945ba1e7250f70cbc8ef6cde0d7809e7a23a94049810f0e77d48383196","source":{"kind":"arxiv","id":"1901.00484","version":1},"attestation_state":"computed","paper":{"title":"Action2Vec: A Crossmodal Embedding Approach to Action Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Silva, James M. Rehg, Meera Hahn","submitted_at":"2019-01-02T18:35:32Z","abstract_excerpt":"We describe a novel cross-modal embedding space for actions, named Action2Vec, which combines linguistic cues from class labels with spatio-temporal features derived from video clips. Our approach uses a hierarchical recurrent network to capture the temporal structure of video features. We train our embedding using a joint loss that combines classification accuracy with similarity to Word2Vec semantics. We evaluate Action2Vec by performing zero shot action recognition and obtain state of the art results on three standard datasets. In addition, we present two novel analogy tests which quantify "},"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":"1901.00484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-02T18:35:32Z","cross_cats_sorted":[],"title_canon_sha256":"bd168a2cec9e0259edac6d8e5b5ab2883349acca66e4afb191c70e243c118af0","abstract_canon_sha256":"f1ba31591c2ba6268d7804d4f91f07088028fd72d3fb321667edd4762bd98a0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:03.709826Z","signature_b64":"E/wg3F6laaB1DSBMdh7y1QmMt55qgr5IEsPwaM3h2gaxVvjFsJeLfRbPIi89/1H9Gmv9e/Eefb2fmyJBVfyNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae9502945ba1e7250f70cbc8ef6cde0d7809e7a23a94049810f0e77d48383196","last_reissued_at":"2026-05-17T23:57:03.709048Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:03.709048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action2Vec: A Crossmodal Embedding Approach to Action Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Silva, James M. Rehg, Meera Hahn","submitted_at":"2019-01-02T18:35:32Z","abstract_excerpt":"We describe a novel cross-modal embedding space for actions, named Action2Vec, which combines linguistic cues from class labels with spatio-temporal features derived from video clips. Our approach uses a hierarchical recurrent network to capture the temporal structure of video features. We train our embedding using a joint loss that combines classification accuracy with similarity to Word2Vec semantics. We evaluate Action2Vec by performing zero shot action recognition and obtain state of the art results on three standard datasets. In addition, we present two novel analogy tests which quantify "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00484","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":"1901.00484","created_at":"2026-05-17T23:57:03.709172+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.00484v1","created_at":"2026-05-17T23:57:03.709172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00484","created_at":"2026-05-17T23:57:03.709172+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2KQFFC3UHTS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2KQFFC3UHTSKD3Q","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2KQFFC3","created_at":"2026-05-18T12:33:30.264802+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/V2KQFFC3UHTSKD3QZPEO63G6BV","json":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV.json","graph_json":"https://pith.science/api/pith-number/V2KQFFC3UHTSKD3QZPEO63G6BV/graph.json","events_json":"https://pith.science/api/pith-number/V2KQFFC3UHTSKD3QZPEO63G6BV/events.json","paper":"https://pith.science/paper/V2KQFFC3"},"agent_actions":{"view_html":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV","download_json":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV.json","view_paper":"https://pith.science/paper/V2KQFFC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.00484&json=true","fetch_graph":"https://pith.science/api/pith-number/V2KQFFC3UHTSKD3QZPEO63G6BV/graph.json","fetch_events":"https://pith.science/api/pith-number/V2KQFFC3UHTSKD3QZPEO63G6BV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV/action/storage_attestation","attest_author":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV/action/author_attestation","sign_citation":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV/action/citation_signature","submit_replication":"https://pith.science/pith/V2KQFFC3UHTSKD3QZPEO63G6BV/action/replication_record"}},"created_at":"2026-05-17T23:57:03.709172+00:00","updated_at":"2026-05-17T23:57:03.709172+00:00"}