{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PBOSBLTL2CZEEQ7LUKVYZYAHSH","short_pith_number":"pith:PBOSBLTL","schema_version":"1.0","canonical_sha256":"785d20ae6bd0b24243eba2ab8ce00791f73939fbd13f4250b9b17a955d045499","source":{"kind":"arxiv","id":"1908.03477","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diane Larlus, Dima Damen, Gabriela Csurka, Michael Wray","submitted_at":"2019-08-09T14:41:06Z","abstract_excerpt":"We address the problem of cross-modal fine-grained action retrieval between text and video. Cross-modal retrieval is commonly achieved through learning a shared embedding space, that can indifferently embed modalities. In this paper, we propose to enrich the embedding by disentangling parts-of-speech (PoS) in the accompanying captions. We build a separate multi-modal embedding space for each PoS tag. The outputs of multiple PoS embeddings are then used as input to an integrated multi-modal space, where we perform action retrieval. All embeddings are trained jointly through a combination of PoS"},"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":"1908.03477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T14:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"1f328ba70a5b22950beb8b2031f8ccfb098b239fb2799a65c9d633e11f22e504","abstract_canon_sha256":"5cef22cf3c03fd0636ca8cde0d2d6a2b86cefc71a497fc46e2739003bb2a233c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:40.283732Z","signature_b64":"44KhrJZJKKQ+tUZRc4qDW3Xy9ebSwCVsjXI7De2C2Spefhpw7i1isp6Cu5LVtY1ai9ie1YcNJSWq+sRVEg4ZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"785d20ae6bd0b24243eba2ab8ce00791f73939fbd13f4250b9b17a955d045499","last_reissued_at":"2026-07-04T23:52:40.283391Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:40.283391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diane Larlus, Dima Damen, Gabriela Csurka, Michael Wray","submitted_at":"2019-08-09T14:41:06Z","abstract_excerpt":"We address the problem of cross-modal fine-grained action retrieval between text and video. Cross-modal retrieval is commonly achieved through learning a shared embedding space, that can indifferently embed modalities. In this paper, we propose to enrich the embedding by disentangling parts-of-speech (PoS) in the accompanying captions. We build a separate multi-modal embedding space for each PoS tag. The outputs of multiple PoS embeddings are then used as input to an integrated multi-modal space, where we perform action retrieval. All embeddings are trained jointly through a combination of PoS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03477","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/1908.03477/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":"1908.03477","created_at":"2026-07-04T23:52:40.283449+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03477v1","created_at":"2026-07-04T23:52:40.283449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03477","created_at":"2026-07-04T23:52:40.283449+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBOSBLTL2CZE","created_at":"2026-07-04T23:52:40.283449+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBOSBLTL2CZEEQ7L","created_at":"2026-07-04T23:52:40.283449+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBOSBLTL","created_at":"2026-07-04T23:52:40.283449+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/PBOSBLTL2CZEEQ7LUKVYZYAHSH","json":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH.json","graph_json":"https://pith.science/api/pith-number/PBOSBLTL2CZEEQ7LUKVYZYAHSH/graph.json","events_json":"https://pith.science/api/pith-number/PBOSBLTL2CZEEQ7LUKVYZYAHSH/events.json","paper":"https://pith.science/paper/PBOSBLTL"},"agent_actions":{"view_html":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH","download_json":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH.json","view_paper":"https://pith.science/paper/PBOSBLTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03477&json=true","fetch_graph":"https://pith.science/api/pith-number/PBOSBLTL2CZEEQ7LUKVYZYAHSH/graph.json","fetch_events":"https://pith.science/api/pith-number/PBOSBLTL2CZEEQ7LUKVYZYAHSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH/action/storage_attestation","attest_author":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH/action/author_attestation","sign_citation":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH/action/citation_signature","submit_replication":"https://pith.science/pith/PBOSBLTL2CZEEQ7LUKVYZYAHSH/action/replication_record"}},"created_at":"2026-07-04T23:52:40.283449+00:00","updated_at":"2026-07-04T23:52:40.283449+00:00"}