{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J2MDVBYFUN3EGDH3TI7ZEXXWWM","short_pith_number":"pith:J2MDVBYF","schema_version":"1.0","canonical_sha256":"4e983a8705a376430cfb9a3f925ef6b30e300fefedab60bda2f51daf64a40c5f","source":{"kind":"arxiv","id":"1902.05829","version":1},"attestation_state":"computed","paper":{"title":"Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Athanasia Zlatintsi, Nikolaos Gkanatsios, Petros Koutras, Petros Maragos, Vassilis Pitsikalis","submitted_at":"2019-02-15T14:53:40Z","abstract_excerpt":"Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised two-branch architecture, the Multimodal Attentional Translation Embeddings, where the visual features of each branch are driven by a multimodal attentional mechanism that exploits spatio-linguistic similarities in a low-dimensional space. We present a variety of experiments comparing against all related approaches in the literature, as well as by "},"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":"1902.05829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-15T14:53:40Z","cross_cats_sorted":[],"title_canon_sha256":"38f7feb79fd690a55f70dba0ecb920eca81cde24548efa45f7f6812e2bbd03eb","abstract_canon_sha256":"27711dccc3bd70ce2385aef546602e442fc8400ed9bdf4a5ed2915d1254b1bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:55.360494Z","signature_b64":"UPbWvggP38g4XfU/QDoP8xDbwnmxvjIOoed7tlIIL7gYgB6bYCL1jCpII7tXhPkWACv48CYANOUDOj45Wq4HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e983a8705a376430cfb9a3f925ef6b30e300fefedab60bda2f51daf64a40c5f","last_reissued_at":"2026-05-17T23:53:55.359760Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:55.359760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Athanasia Zlatintsi, Nikolaos Gkanatsios, Petros Koutras, Petros Maragos, Vassilis Pitsikalis","submitted_at":"2019-02-15T14:53:40Z","abstract_excerpt":"Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised two-branch architecture, the Multimodal Attentional Translation Embeddings, where the visual features of each branch are driven by a multimodal attentional mechanism that exploits spatio-linguistic similarities in a low-dimensional space. We present a variety of experiments comparing against all related approaches in the literature, as well as by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05829","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":""},"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":"1902.05829","created_at":"2026-05-17T23:53:55.359865+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05829v1","created_at":"2026-05-17T23:53:55.359865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05829","created_at":"2026-05-17T23:53:55.359865+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2MDVBYFUN3E","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2MDVBYFUN3EGDH3","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2MDVBYF","created_at":"2026-05-18T12:33:18.533446+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/J2MDVBYFUN3EGDH3TI7ZEXXWWM","json":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM.json","graph_json":"https://pith.science/api/pith-number/J2MDVBYFUN3EGDH3TI7ZEXXWWM/graph.json","events_json":"https://pith.science/api/pith-number/J2MDVBYFUN3EGDH3TI7ZEXXWWM/events.json","paper":"https://pith.science/paper/J2MDVBYF"},"agent_actions":{"view_html":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM","download_json":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM.json","view_paper":"https://pith.science/paper/J2MDVBYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05829&json=true","fetch_graph":"https://pith.science/api/pith-number/J2MDVBYFUN3EGDH3TI7ZEXXWWM/graph.json","fetch_events":"https://pith.science/api/pith-number/J2MDVBYFUN3EGDH3TI7ZEXXWWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM/action/storage_attestation","attest_author":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM/action/author_attestation","sign_citation":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM/action/citation_signature","submit_replication":"https://pith.science/pith/J2MDVBYFUN3EGDH3TI7ZEXXWWM/action/replication_record"}},"created_at":"2026-05-17T23:53:55.359865+00:00","updated_at":"2026-05-17T23:53:55.359865+00:00"}