{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:33JTS7HFEW44OZSDFWZIJYEZCS","short_pith_number":"pith:33JTS7HF","schema_version":"1.0","canonical_sha256":"ded3397ce525b9c766432db284e09914b40ecfec24fad8f5f0955c950e5e7622","source":{"kind":"arxiv","id":"1901.02662","version":3},"attestation_state":"computed","paper":{"title":"Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Tang, Lu Jin, Zechao Li","submitted_at":"2019-01-09T10:27:57Z","abstract_excerpt":"Hashing has been widely applied to multimodal retrieval on large-scale multimedia data due to its efficiency in computation and storage. In this article, we propose a novel deep semantic multimodal hashing network (DSMHN) for scalable image-text and video-text retrieval. The proposed deep hashing framework leverages 2-D convolutional neural networks (CNN) as the backbone network to capture the spatial information for image-text retrieval, while the 3-D CNN as the backbone network to capture the spatial and temporal information for video-text retrieval. In the DSMHN, two sets of modality-specif"},"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":"1901.02662","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-09T10:27:57Z","cross_cats_sorted":[],"title_canon_sha256":"26a4fa601b913f3be800321a9e8c993805370e00644a5d02a9aea072e5667512","abstract_canon_sha256":"13140101b310cd20f185af1af6b5bb4e0c0f41d5c719dddea4ecc7baaa77dd7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:59.934097Z","signature_b64":"A9raY3ku+O46VkBH+VxryYIXsyN9ZpNNCMpGoG1Z1o9S03KCDKxQ7Feib+3dkQAeWKLsk7QiqBsq61LF0agBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ded3397ce525b9c766432db284e09914b40ecfec24fad8f5f0955c950e5e7622","last_reissued_at":"2026-07-05T03:45:59.933497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:59.933497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Tang, Lu Jin, Zechao Li","submitted_at":"2019-01-09T10:27:57Z","abstract_excerpt":"Hashing has been widely applied to multimodal retrieval on large-scale multimedia data due to its efficiency in computation and storage. In this article, we propose a novel deep semantic multimodal hashing network (DSMHN) for scalable image-text and video-text retrieval. The proposed deep hashing framework leverages 2-D convolutional neural networks (CNN) as the backbone network to capture the spatial information for image-text retrieval, while the 3-D CNN as the backbone network to capture the spatial and temporal information for video-text retrieval. In the DSMHN, two sets of modality-specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02662","kind":"arxiv","version":3},"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/1901.02662/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":"1901.02662","created_at":"2026-07-05T03:45:59.933566+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02662v3","created_at":"2026-07-05T03:45:59.933566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02662","created_at":"2026-07-05T03:45:59.933566+00:00"},{"alias_kind":"pith_short_12","alias_value":"33JTS7HFEW44","created_at":"2026-07-05T03:45:59.933566+00:00"},{"alias_kind":"pith_short_16","alias_value":"33JTS7HFEW44OZSD","created_at":"2026-07-05T03:45:59.933566+00:00"},{"alias_kind":"pith_short_8","alias_value":"33JTS7HF","created_at":"2026-07-05T03:45:59.933566+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/33JTS7HFEW44OZSDFWZIJYEZCS","json":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS.json","graph_json":"https://pith.science/api/pith-number/33JTS7HFEW44OZSDFWZIJYEZCS/graph.json","events_json":"https://pith.science/api/pith-number/33JTS7HFEW44OZSDFWZIJYEZCS/events.json","paper":"https://pith.science/paper/33JTS7HF"},"agent_actions":{"view_html":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS","download_json":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS.json","view_paper":"https://pith.science/paper/33JTS7HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02662&json=true","fetch_graph":"https://pith.science/api/pith-number/33JTS7HFEW44OZSDFWZIJYEZCS/graph.json","fetch_events":"https://pith.science/api/pith-number/33JTS7HFEW44OZSDFWZIJYEZCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS/action/storage_attestation","attest_author":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS/action/author_attestation","sign_citation":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS/action/citation_signature","submit_replication":"https://pith.science/pith/33JTS7HFEW44OZSDFWZIJYEZCS/action/replication_record"}},"created_at":"2026-07-05T03:45:59.933566+00:00","updated_at":"2026-07-05T03:45:59.933566+00:00"}