{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7SQYY32TXJD4A46WXJUZNM2ER6","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":"03600312c98a381391966edd82a792266bdac3807a07f649024eee190c9a9a7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:55:44Z","title_canon_sha256":"719c0267dd2f1824658eee63b7fb9fd14dc2a61c0255ae55e459490151b44814"},"schema_version":"1.0","source":{"id":"1709.01362","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01362","created_at":"2026-05-18T00:10:47Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01362v3","created_at":"2026-05-18T00:10:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01362","created_at":"2026-05-18T00:10:47Z"},{"alias_kind":"pith_short_12","alias_value":"7SQYY32TXJD4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7SQYY32TXJD4A46W","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7SQYY32T","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:29f4be370c84e5545e9010b9a08fa5fea6fbccb494ff7b60be2396f9f0a60717","target":"graph","created_at":"2026-05-18T00:10:47Z","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"},"paper":{"abstract_excerpt":"This paper strives to find amidst a set of sentences the one best describing the content of a given image or video. Different from existing works, which rely on a joint subspace for their image and video caption retrieval, we propose to do so in a visual space exclusively. Apart from this conceptual novelty, we contribute \\emph{Word2VisualVec}, a deep neural network architecture that learns to predict a visual feature representation from textual input. Example captions are encoded into a textual embedding based on multi-scale sentence vectorization and further transferred into a deep visual fe","authors_text":"Cees G. M. Snoek, Jianfeng Dong, Xirong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:55:44Z","title":"Predicting Visual Features from Text for Image and Video Caption Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01362","kind":"arxiv","version":3},"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":"sha256:1650beb3af1491dda960f7272329ab5e445ee71ef6e1407a84ad61182484f197","target":"record","created_at":"2026-05-18T00:10:47Z","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":"03600312c98a381391966edd82a792266bdac3807a07f649024eee190c9a9a7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:55:44Z","title_canon_sha256":"719c0267dd2f1824658eee63b7fb9fd14dc2a61c0255ae55e459490151b44814"},"schema_version":"1.0","source":{"id":"1709.01362","kind":"arxiv","version":3}},"canonical_sha256":"fca18c6f53ba47c073d6ba6996b3448f9f144452a15dd190f59eb8140e9ac98b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fca18c6f53ba47c073d6ba6996b3448f9f144452a15dd190f59eb8140e9ac98b","first_computed_at":"2026-05-18T00:10:47.493904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:47.493904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OBy6/RdhFJbQR9ugQKvkDO7ODOT8/U9I8JxW0hLRMTWxhwFHLc0Xy6uUciVSRQcsDn9i3271sytlF8pzVnLRAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:47.494534Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.01362","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1650beb3af1491dda960f7272329ab5e445ee71ef6e1407a84ad61182484f197","sha256:29f4be370c84e5545e9010b9a08fa5fea6fbccb494ff7b60be2396f9f0a60717"],"state_sha256":"9ff6674b98ff2f71609d530bf1cfe3818033555ec8a47ae534561ab0b84f8996"}