{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MHK2YSTDGH5LCXQEUNRPFWNJDH","short_pith_number":"pith:MHK2YSTD","schema_version":"1.0","canonical_sha256":"61d5ac4a6331fab15e04a362f2d9a919d4d5af4be98cd77e0811d1d1199031c1","source":{"kind":"arxiv","id":"2107.05448","version":1},"attestation_state":"computed","paper":{"title":"Scenes and Surroundings: Scene Graph Generation using Relation Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Poulami Sinhamahapatra, Rajat Koner, Volker Tresp","submitted_at":"2021-07-12T14:22:20Z","abstract_excerpt":"Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships remain a challenging task. This work proposes a novel local-context aware architecture named relation transformer, which exploits complex global objects to object and object to edge (relation) interactions. Our hierarchical multi-head attention-based approach efficiently captures contextual dependencies between objects and predicts their relationships. In compari"},"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":"2107.05448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-12T14:22:20Z","cross_cats_sorted":[],"title_canon_sha256":"04df41d21e72c2acb597427b9897343582e8a2cdb43cb0b20a2ba1561e45abd8","abstract_canon_sha256":"9967079924eadc5965d2a8b57751990fdbf427899d4067a82a9097cdc5a66ebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:02.865184Z","signature_b64":"UXBUdVc85iENO66NwPlfn1cZfrfPD/T3PsoQWW3ctugTWFp930/9GcwirbCmhNxq9rfB+FeEn5N/VveILHceBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d5ac4a6331fab15e04a362f2d9a919d4d5af4be98cd77e0811d1d1199031c1","last_reissued_at":"2026-07-05T02:57:02.864840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:02.864840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scenes and Surroundings: Scene Graph Generation using Relation Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Poulami Sinhamahapatra, Rajat Koner, Volker Tresp","submitted_at":"2021-07-12T14:22:20Z","abstract_excerpt":"Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships remain a challenging task. This work proposes a novel local-context aware architecture named relation transformer, which exploits complex global objects to object and object to edge (relation) interactions. Our hierarchical multi-head attention-based approach efficiently captures contextual dependencies between objects and predicts their relationships. In compari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05448","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.05448/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":"2107.05448","created_at":"2026-07-05T02:57:02.864895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.05448v1","created_at":"2026-07-05T02:57:02.864895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05448","created_at":"2026-07-05T02:57:02.864895+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHK2YSTDGH5L","created_at":"2026-07-05T02:57:02.864895+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHK2YSTDGH5LCXQE","created_at":"2026-07-05T02:57:02.864895+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHK2YSTD","created_at":"2026-07-05T02:57:02.864895+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/MHK2YSTDGH5LCXQEUNRPFWNJDH","json":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH.json","graph_json":"https://pith.science/api/pith-number/MHK2YSTDGH5LCXQEUNRPFWNJDH/graph.json","events_json":"https://pith.science/api/pith-number/MHK2YSTDGH5LCXQEUNRPFWNJDH/events.json","paper":"https://pith.science/paper/MHK2YSTD"},"agent_actions":{"view_html":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH","download_json":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH.json","view_paper":"https://pith.science/paper/MHK2YSTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.05448&json=true","fetch_graph":"https://pith.science/api/pith-number/MHK2YSTDGH5LCXQEUNRPFWNJDH/graph.json","fetch_events":"https://pith.science/api/pith-number/MHK2YSTDGH5LCXQEUNRPFWNJDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH/action/storage_attestation","attest_author":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH/action/author_attestation","sign_citation":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH/action/citation_signature","submit_replication":"https://pith.science/pith/MHK2YSTDGH5LCXQEUNRPFWNJDH/action/replication_record"}},"created_at":"2026-07-05T02:57:02.864895+00:00","updated_at":"2026-07-05T02:57:02.864895+00:00"}