{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PBOSBLTL2CZEEQ7LUKVYZYAHSH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5cef22cf3c03fd0636ca8cde0d2d6a2b86cefc71a497fc46e2739003bb2a233c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T14:41:06Z","title_canon_sha256":"1f328ba70a5b22950beb8b2031f8ccfb098b239fb2799a65c9d633e11f22e504"},"schema_version":"1.0","source":{"id":"1908.03477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03477","created_at":"2026-07-04T23:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03477v1","created_at":"2026-07-04T23:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03477","created_at":"2026-07-04T23:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"PBOSBLTL2CZE","created_at":"2026-07-04T23:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"PBOSBLTL2CZEEQ7L","created_at":"2026-07-04T23:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"PBOSBLTL","created_at":"2026-07-04T23:52:40Z"}],"graph_snapshots":[{"event_id":"sha256:e448b163a214810c4009f34410d52fb62a64ef385c2676f05b9278ef99c51ca7","target":"graph","created_at":"2026-07-04T23:52:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.03477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Diane Larlus, Dima Damen, Gabriela Csurka, Michael Wray","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T14:41:06Z","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03477","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3de119927910d8567364bde587c5fa4aee60c6109eeb6969e6d799c15d17bc0b","target":"record","created_at":"2026-07-04T23:52:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5cef22cf3c03fd0636ca8cde0d2d6a2b86cefc71a497fc46e2739003bb2a233c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T14:41:06Z","title_canon_sha256":"1f328ba70a5b22950beb8b2031f8ccfb098b239fb2799a65c9d633e11f22e504"},"schema_version":"1.0","source":{"id":"1908.03477","kind":"arxiv","version":1}},"canonical_sha256":"785d20ae6bd0b24243eba2ab8ce00791f73939fbd13f4250b9b17a955d045499","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"785d20ae6bd0b24243eba2ab8ce00791f73939fbd13f4250b9b17a955d045499","first_computed_at":"2026-07-04T23:52:40.283391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:52:40.283391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"44KhrJZJKKQ+tUZRc4qDW3Xy9ebSwCVsjXI7De2C2Spefhpw7i1isp6Cu5LVtY1ai9ie1YcNJSWq+sRVEg4ZBw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:52:40.283732Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.03477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3de119927910d8567364bde587c5fa4aee60c6109eeb6969e6d799c15d17bc0b","sha256:e448b163a214810c4009f34410d52fb62a64ef385c2676f05b9278ef99c51ca7"],"state_sha256":"affec6a37114464c40b55af4a5d8e44df24da312ac84a7d81c7e4e92e5efe8d1"}