{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DFO3HCMFQCQCCMH7IK2VRROC5O","short_pith_number":"pith:DFO3HCMF","schema_version":"1.0","canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","source":{"kind":"arxiv","id":"1604.06838","version":2},"attestation_state":"computed","paper":{"title":"Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Jianfeng Dong, Xirong Li","submitted_at":"2016-04-23T00:28:17Z","abstract_excerpt":"This paper strives to find the sentence best describing the content of an image or video. Different from existing works, which rely on a joint subspace for image / video to sentence matching, we propose to do so in a visual space only. We contribute Word2VisualVec, a deep neural network architecture that learns to predict a deep visual encoding of textual input based on sentence vectorization and a multi-layer perceptron. We thoroughly analyze its architectural design, by varying the sentence vectorization strategy, network depth and the deep feature to predict for image to sentence matching. "},"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":"1604.06838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-23T00:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"e003f3f3f477ea432553c2d895e8d2b29955d3040e282d8d7fcc68d0b59b2698","abstract_canon_sha256":"12967f674362e969c8608606b57c38c8db4417e39f965245fd36dcfc04313742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:46.182632Z","signature_b64":"Tx02QT1MvqJv03hse+r/urewOm1zutPUxgujK0Rdxm8Hy/de9awXnZBcmhGfwdpD5DaHGEnRJelasAjNyBeJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","last_reissued_at":"2026-05-18T00:56:46.182054Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:46.182054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Jianfeng Dong, Xirong Li","submitted_at":"2016-04-23T00:28:17Z","abstract_excerpt":"This paper strives to find the sentence best describing the content of an image or video. Different from existing works, which rely on a joint subspace for image / video to sentence matching, we propose to do so in a visual space only. We contribute Word2VisualVec, a deep neural network architecture that learns to predict a deep visual encoding of textual input based on sentence vectorization and a multi-layer perceptron. We thoroughly analyze its architectural design, by varying the sentence vectorization strategy, network depth and the deep feature to predict for image to sentence matching. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06838","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":"1604.06838","created_at":"2026-05-18T00:56:46.182161+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.06838v2","created_at":"2026-05-18T00:56:46.182161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06838","created_at":"2026-05-18T00:56:46.182161+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFO3HCMFQCQC","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFO3HCMFQCQCCMH7","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFO3HCMF","created_at":"2026-05-18T12:30:12.583610+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/DFO3HCMFQCQCCMH7IK2VRROC5O","json":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O.json","graph_json":"https://pith.science/api/pith-number/DFO3HCMFQCQCCMH7IK2VRROC5O/graph.json","events_json":"https://pith.science/api/pith-number/DFO3HCMFQCQCCMH7IK2VRROC5O/events.json","paper":"https://pith.science/paper/DFO3HCMF"},"agent_actions":{"view_html":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O","download_json":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O.json","view_paper":"https://pith.science/paper/DFO3HCMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.06838&json=true","fetch_graph":"https://pith.science/api/pith-number/DFO3HCMFQCQCCMH7IK2VRROC5O/graph.json","fetch_events":"https://pith.science/api/pith-number/DFO3HCMFQCQCCMH7IK2VRROC5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/action/storage_attestation","attest_author":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/action/author_attestation","sign_citation":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/action/citation_signature","submit_replication":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/action/replication_record"}},"created_at":"2026-05-18T00:56:46.182161+00:00","updated_at":"2026-05-18T00:56:46.182161+00:00"}