{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DAUISZRUILI35FI3TUPYFRTIIK","short_pith_number":"pith:DAUISZRU","schema_version":"1.0","canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","source":{"kind":"arxiv","id":"2004.06193","version":2},"attestation_state":"computed","paper":{"title":"Relation Transformer Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rajat Koner, Suprosanna Shit, Volker Tresp","submitted_at":"2020-04-13T20:47:01Z","abstract_excerpt":"The extraction of a scene graph with objects as nodes and mutual relationships as edges is the basis for a deep understanding of image content. Despite recent advances, such as message passing and joint classification, the detection of visual relationships remains a challenging task due to sub-optimal exploration of the mutual interaction among the visual objects. In this work, we propose a novel transformer formulation for scene graph generation and relation prediction. We leverage the encoder-decoder architecture of the transformer for rich feature embedding of nodes and edges. Specifically,"},"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":"2004.06193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T20:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"90972d4cd7a42bd1690f560d0c7420dc9d5644ba889c128e95929911bdfe7542","abstract_canon_sha256":"9a104015c77f0baf022f4157c2fd0e6f11f3643425b9d5b28ca1c8f61d15a8c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:34.721108Z","signature_b64":"Jjahx4ygfpL+QWgOLr9azmkrk4nxZ3YHV6tf+K8eCxZjuRqhpevIKl7AqvES4kgnYCOQEvMIpGoH9CZLWnWkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"182889663442d1be951b9d1f82c66842a4464194d4283bdd69728fae64ab19fd","last_reissued_at":"2026-07-05T02:59:34.720727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:34.720727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relation Transformer Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rajat Koner, Suprosanna Shit, Volker Tresp","submitted_at":"2020-04-13T20:47:01Z","abstract_excerpt":"The extraction of a scene graph with objects as nodes and mutual relationships as edges is the basis for a deep understanding of image content. Despite recent advances, such as message passing and joint classification, the detection of visual relationships remains a challenging task due to sub-optimal exploration of the mutual interaction among the visual objects. In this work, we propose a novel transformer formulation for scene graph generation and relation prediction. We leverage the encoder-decoder architecture of the transformer for rich feature embedding of nodes and edges. Specifically,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06193","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.06193/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":"2004.06193","created_at":"2026-07-05T02:59:34.720781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.06193v2","created_at":"2026-07-05T02:59:34.720781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06193","created_at":"2026-07-05T02:59:34.720781+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAUISZRUILI3","created_at":"2026-07-05T02:59:34.720781+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAUISZRUILI35FI3","created_at":"2026-07-05T02:59:34.720781+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAUISZRU","created_at":"2026-07-05T02:59:34.720781+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/DAUISZRUILI35FI3TUPYFRTIIK","json":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK.json","graph_json":"https://pith.science/api/pith-number/DAUISZRUILI35FI3TUPYFRTIIK/graph.json","events_json":"https://pith.science/api/pith-number/DAUISZRUILI35FI3TUPYFRTIIK/events.json","paper":"https://pith.science/paper/DAUISZRU"},"agent_actions":{"view_html":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK","download_json":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK.json","view_paper":"https://pith.science/paper/DAUISZRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.06193&json=true","fetch_graph":"https://pith.science/api/pith-number/DAUISZRUILI35FI3TUPYFRTIIK/graph.json","fetch_events":"https://pith.science/api/pith-number/DAUISZRUILI35FI3TUPYFRTIIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/action/storage_attestation","attest_author":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/action/author_attestation","sign_citation":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/action/citation_signature","submit_replication":"https://pith.science/pith/DAUISZRUILI35FI3TUPYFRTIIK/action/replication_record"}},"created_at":"2026-07-05T02:59:34.720781+00:00","updated_at":"2026-07-05T02:59:34.720781+00:00"}