{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KEV44RPHGULWUN2WHFELWYAVIH","short_pith_number":"pith:KEV44RPH","schema_version":"1.0","canonical_sha256":"512bce45e735176a37563948bb601541c88f3e7bd0c1e2094cd253ec58c12ee0","source":{"kind":"arxiv","id":"2303.05342","version":1},"attestation_state":"computed","paper":{"title":"Knowledge-augmented Few-shot Visual Relation Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bei Wu, Dongxiao Huang, Hai-Tao Zheng, Jiaoyan Chen, Qingbin Liu, Tianyu Yu, Wenqiang Liu, Xi Chen, Yangning Li, Yexin Wang, Yinghui Li","submitted_at":"2023-03-09T15:38:40Z","abstract_excerpt":"Visual Relation Detection (VRD) aims to detect relationships between objects for image understanding. Most existing VRD methods rely on thousands of training samples of each relationship to achieve satisfactory performance. Some recent papers tackle this problem by few-shot learning with elaborately designed pipelines and pre-trained word vectors. However, the performance of existing few-shot VRD models is severely hampered by the poor generalization capability, as they struggle to handle the vast semantic diversity of visual relationships. Nonetheless, humans have the ability to learn new rel"},"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":"2303.05342","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T15:38:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"06276ab98b2ed8b22d15ac97873b727b3a0287def6d3407a8f9c52101778aa7b","abstract_canon_sha256":"de5627228611c2becf619677c0a000a1d96359625d993052b8e13d481e8a9afb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:39.738038Z","signature_b64":"MjxuF8twlqx8V1rdSHxX/RonzzvxiSFwUNK11g+G4Z1fVtu94TzEPHNSf8tCOh+TmelpDo+fncQrmxU+jiSRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"512bce45e735176a37563948bb601541c88f3e7bd0c1e2094cd253ec58c12ee0","last_reissued_at":"2026-07-05T05:49:39.737576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:39.737576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-augmented Few-shot Visual Relation Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bei Wu, Dongxiao Huang, Hai-Tao Zheng, Jiaoyan Chen, Qingbin Liu, Tianyu Yu, Wenqiang Liu, Xi Chen, Yangning Li, Yexin Wang, Yinghui Li","submitted_at":"2023-03-09T15:38:40Z","abstract_excerpt":"Visual Relation Detection (VRD) aims to detect relationships between objects for image understanding. Most existing VRD methods rely on thousands of training samples of each relationship to achieve satisfactory performance. Some recent papers tackle this problem by few-shot learning with elaborately designed pipelines and pre-trained word vectors. However, the performance of existing few-shot VRD models is severely hampered by the poor generalization capability, as they struggle to handle the vast semantic diversity of visual relationships. Nonetheless, humans have the ability to learn new rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05342","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/2303.05342/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":"2303.05342","created_at":"2026-07-05T05:49:39.737634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05342v1","created_at":"2026-07-05T05:49:39.737634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05342","created_at":"2026-07-05T05:49:39.737634+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEV44RPHGULW","created_at":"2026-07-05T05:49:39.737634+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEV44RPHGULWUN2W","created_at":"2026-07-05T05:49:39.737634+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEV44RPH","created_at":"2026-07-05T05:49:39.737634+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/KEV44RPHGULWUN2WHFELWYAVIH","json":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH.json","graph_json":"https://pith.science/api/pith-number/KEV44RPHGULWUN2WHFELWYAVIH/graph.json","events_json":"https://pith.science/api/pith-number/KEV44RPHGULWUN2WHFELWYAVIH/events.json","paper":"https://pith.science/paper/KEV44RPH"},"agent_actions":{"view_html":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH","download_json":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH.json","view_paper":"https://pith.science/paper/KEV44RPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05342&json=true","fetch_graph":"https://pith.science/api/pith-number/KEV44RPHGULWUN2WHFELWYAVIH/graph.json","fetch_events":"https://pith.science/api/pith-number/KEV44RPHGULWUN2WHFELWYAVIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH/action/storage_attestation","attest_author":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH/action/author_attestation","sign_citation":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH/action/citation_signature","submit_replication":"https://pith.science/pith/KEV44RPHGULWUN2WHFELWYAVIH/action/replication_record"}},"created_at":"2026-07-05T05:49:39.737634+00:00","updated_at":"2026-07-05T05:49:39.737634+00:00"}