{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HDLTRADBTFJWLIQOPKVWH4373R","short_pith_number":"pith:HDLTRADB","schema_version":"1.0","canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","source":{"kind":"arxiv","id":"1707.09700","version":2},"attestation_state":"computed","paper":{"title":"Scene Graph Generation from Objects, Phrases and Region Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Kun Wang, Wanli Ouyang, Xiaogang Wang, Yikang Li","submitted_at":"2017-07-31T02:40:19Z","abstract_excerpt":"Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision"},"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":"1707.09700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-31T02:40:19Z","cross_cats_sorted":[],"title_canon_sha256":"ee7c327e178ca839203a9af78eff25e7ea518b03009bbf7af223875a96218dd4","abstract_canon_sha256":"b8e220dd3567530dbdbe6b59a3a6a9e1a2838b92ea4e861a7c595bc7694e54d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:08.939415Z","signature_b64":"PBzLqx+EajQ+b4YPclj3IhvxLsASPBMBhIUSSty5cOZb0/NOCarTZe0VIlyOM1lw5FoDRO7gO1GI/N2TPGTrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38d7388061995365a20e7aab63f37fdc41e11bd4d7fda907f5ba00e93d50b493","last_reissued_at":"2026-05-18T00:35:08.938988Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:08.938988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scene Graph Generation from Objects, Phrases and Region Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Kun Wang, Wanli Ouyang, Xiaogang Wang, Yikang Li","submitted_at":"2017-07-31T02:40:19Z","abstract_excerpt":"Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09700","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":"1707.09700","created_at":"2026-05-18T00:35:08.939042+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09700v2","created_at":"2026-05-18T00:35:08.939042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09700","created_at":"2026-05-18T00:35:08.939042+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDLTRADBTFJW","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDLTRADBTFJWLIQO","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDLTRADB","created_at":"2026-05-18T12:31:18.294218+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/HDLTRADBTFJWLIQOPKVWH4373R","json":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R.json","graph_json":"https://pith.science/api/pith-number/HDLTRADBTFJWLIQOPKVWH4373R/graph.json","events_json":"https://pith.science/api/pith-number/HDLTRADBTFJWLIQOPKVWH4373R/events.json","paper":"https://pith.science/paper/HDLTRADB"},"agent_actions":{"view_html":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R","download_json":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R.json","view_paper":"https://pith.science/paper/HDLTRADB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09700&json=true","fetch_graph":"https://pith.science/api/pith-number/HDLTRADBTFJWLIQOPKVWH4373R/graph.json","fetch_events":"https://pith.science/api/pith-number/HDLTRADBTFJWLIQOPKVWH4373R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/action/storage_attestation","attest_author":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/action/author_attestation","sign_citation":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/action/citation_signature","submit_replication":"https://pith.science/pith/HDLTRADBTFJWLIQOPKVWH4373R/action/replication_record"}},"created_at":"2026-05-18T00:35:08.939042+00:00","updated_at":"2026-05-18T00:35:08.939042+00:00"}